Pith. sign in

REVIEW 2 major objections 5 minor 89 references

Explicit frequency-spatial collaboration in a DETR raises small-object AP by about 7 points on drone and aerial benchmarks.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.5

2026-07-11 07:49 UTC pith:O5X4TUDT

load-bearing objection Solid empirical DETR upgrade for aerial SOD: three coherent frequency-spatial modules deliver real ~6.5 AP / ~7 APS gains on VisDrone and AITODv2 with clean ablations and code. the 2 major comments →

arxiv 2607.05176 v2 pith:O5X4TUDT submitted 2026-07-06 cs.CV

FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small Object Detection

Aiwen Liu , Chengguang Zhu , Gang Wang , Dandan Zhu , Haodong Lin , Yan Wang , Huiyu Zhou , Zhengyi Pan This is my paper
classification cs.CV
keywords small object detectiondetection transformerfrequency-spatial collaborative modelingmulti-scale feature fusionwavelet downsamplingVisDroneAITOD
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Small objects occupy few pixels, so the high-frequency cues that mark their edges and texture are easily erased when detectors fuse features and shrink resolution. This paper claims that ordinary hybrid DETR pipelines mix spatial pooling with frequency aliasing and truncation, and that the resulting loss of high-frequency detail is a central reason small-object detection still lags. The authors therefore build FSDC-DETR, an end-to-end transformer that deliberately constructs, shunts, and protects complementary frequency and spatial representations at every stage of the backbone and encoder. Three linked modules do the work: an adaptive dual-branch fusion that diversifies and selects spectral content, a shunt fusion that lets frequency and spatial streams refine each other across scales, and a wavelet-style dynamic downsampler that keeps informative high-frequency sub-bands alive during resolution changes. On VisDrone and AITOD the design lifts overall AP by more than six points and small-object AP by nearly seven, showing that restoring frequency integrity can translate into clearer localization of tiny targets.

Core claim

Existing DETR-style detectors for small objects suffer because spatial aggregation and downsampling entangle with implicit frequency aliasing and truncation; explicitly constructing, propagating, and preserving complementary frequency-spatial representations with DBFSAF, SFS-FF and FSD-Down recovers the high-frequency cues needed for precise small-object localization and yields state-of-the-art gains of roughly 6–7 AP on VisDrone-DET2019 and AITODv2.

What carries the argument

The frequency-spatial collaborative pipeline (DBFSAF for adaptive dual-branch spectral fusion and partial refinement, SFS-FF for bidirectional shunt fusion inside the hybrid encoder, and FSD-Down for learnable wavelet-grouped downsampling) that keeps high-frequency sub-bands alive while features move across scales.

Load-bearing premise

The main reason current hybrid DETR encoders miss small objects is that they erase high-frequency detail during ordinary spatial fusion and downsampling; if the real bottleneck is elsewhere (context, queries, or labels), the frequency modules would not produce the reported gains.

What would settle it

Replace FSD-Down and the frequency shunt with ordinary strided convolution and concatenation while keeping every other architectural choice identical; if small-object AP on VisDrone and AITOD no longer rises by several points, the frequency-preservation claim fails.

Watch this falsifier. Get emailed when new claim-graph text bears on it.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

2 major / 5 minor

Summary. The paper proposes FSDC-DETR, a DETR-style detector for small object detection that explicitly models complementary frequency and spatial representations. Built on a dual-branch DEIMv2-style backbone (CNN + DINOv3 ViT), it introduces three modules: DBFSAF (FDConv + partial frequency-spatial refinement with MKSRU/FPU) to diversify and preserve high-frequency cues at fusion; SFS-FF inside a hybrid encoder that shunts features into FFT-based frequency and spatial refine paths for cross-scale aggregation; and FSD-Down, a learnable wavelet/grouped-convolution downsampler that retains high-frequency sub-bands during scale transitions. On VisDrone-DET2019 and AITODv2 (800 imes800), the method reports SOTA AP of 31.1 / 32.3, with APS gains of +6.8 / +6.9 over DEIMv2-L, supported by module ablations, a partial-ratio study, frequency-response plots, and qualitative detections. Code is released.

Significance. If the reported gains hold under standard multi-seed evaluation, the work is a solid empirical contribution to real-time DETR-style SOD. It targets a recognized failure mode (high-frequency attenuation in multi-scale fusion) with a coherent three-stage pipeline, demonstrates large APS lifts on two hard aerial benchmarks against recent YOLO and DETR baselines at multiple scales, and provides additive ablations plus a public implementation. The combination of dual-branch frequency-aware fusion, FFT shunt fusion, and wavelet-style dynamic downsampling is a useful architectural pattern for the community even if residual gains partly arise from capacity or training recipe.

major comments (2)
  1. Table 1 and §4.4 report single-run AP numbers without error bars, multiple random seeds, or variance estimates. Given that the central claim is a ~6.4–6.6 AP (and ~6.8–6.9 APS) SOTA margin over strong DETR baselines, at least 3-seed means ± std (or an equivalent multi-run protocol) on the official test splits are needed to establish that the gains are stable rather than run-specific.
  2. §4.2 and Table 1 compare FSDC-DETR (40.3 M) primarily against DEIMv2-L (32 M) and other L/X variants, while the training recipe (MixUp/Mosaic/CopyBlend, dense O2O schedule, 100 epochs, 800×800) is inherited from DEIMv2. A capacity-matched or FLOPs-matched control (e.g., DEIMv2-L with extra multi-scale fusion layers or width scaling to ~40 M under the identical recipe) is required to isolate the contribution of DBFSAF/SFS-FF/FSD-Down from parameter count and optimization differences; the supplement mention of an enhanced DEIMv2-L baseline should be moved into the main Table 1 or an expanded ablation.
minor comments (5)
  1. Fig. 1 frequency-response curves lack axis units, exact layer/channel selection protocol, and a quantitative bandwidth or high-frequency energy metric; a short methods note would make the spectral claim more reproducible.
  2. Eqs. (1)–(6) and (10)–(13) introduce several free scalars (γ, α, β, ρ) and channel splits (C/2, 3C/8, C/8); a compact hyper-parameter table or default values in the main text would aid re-implementation.
  3. Notation is slightly inconsistent (F^P_L / F^P_H vs. Fin / ˆFin; Partial_γ vs. γ in text); unify symbols across §3.2–3.4.
  4. Related Work §2.3 could more explicitly position FSD-Down against HWD and UAV-DETR’s frequency-focused downsampling beyond the brief contrast in §3.4.
  5. Minor typos and formatting: “state-of-the-artperformance”, missing spaces around citations, and occasional line-break artifacts in the arXiv PDF.

Circularity Check

0 steps flagged

No significant circularity: empirical architecture paper whose SOTA claims rest on held-out test metrics and additive ablations, not on self-definitional equations or fitted-as-prediction steps.

full rationale

FSDC-DETR is a standard computer-vision architecture paper. Its central claim is empirical (AP +6.4 / +6.6 and APS +6.8 / +6.9 on the official VisDrone-DET2019 and AITODv2 test splits relative to DEIMv2-L and other published DETR/YOLO baselines). The three modules (DBFSAF Eqs. 1–9, SFS-FF Eqs. 10–11, FSD-Down Eqs. 12–13) are design choices that introduce learnable frequency-spatial operators; none of them defines a target metric in terms of itself, nor do they fit a free parameter on a subset of the evaluation data and then re-label that fit as a prediction. Table 2 shows complementary, additive lifts when the modules are stacked; Fig. 1 is a qualitative spectral illustration, not a fitted constant. Self-citations (DEIMv2, RT-DETR, FDConv, SFS-Conv, HWD, etc.) supply architectural priors and baselines; they are not uniqueness theorems that force the reported AP numbers. Because the derivation chain never reduces a claimed result to its own inputs by construction, the circularity score is 0.

Axiom & Free-Parameter Ledger

3 free parameters · 3 axioms · 3 invented entities

Standard supervised detection setup plus a handful of architectural hyper-parameters and the modeling premise that high-frequency preservation is the key SOD bottleneck. No new physical entities; the three modules are engineered components whose value is measured empirically.

free parameters (3)
  • partial ratio γ in DBFSAF = 0.5
    Channel split fraction for frequency-spatial refinement; ablated and set to 0.5 for best AP.
  • learnable scalars α, β, ρ
    Channel-attention and frequency-modulation scales inside PFSR and FSD-Down; optimized end-to-end.
  • AdamW learning rate / weight decay / batch size / epochs = 5e-4 / 1.25e-4 / 64 / 100
    Training hyper-parameters chosen following DEIMv2 and tuned for the reported runs.
axioms (3)
  • domain assumption High-frequency components are critical for small-object localization and are systematically attenuated by conventional multi-scale fusion and strided convolution.
    Stated in Introduction and used to motivate all three modules; supported by frequency-response plots but not proven universal.
  • domain assumption ViT branches act as low-pass filters while CNN branches preserve high-frequency content, so explicit frequency-aware fusion is required.
    Cited from prior spectral analyses of ViTs/CNNs and illustrated in Fig. 1.
  • standard math Standard DETR set-prediction loss, bipartite matching, and multi-scale feature pyramid assumptions hold.
    Inherited from the DEIMv2 / RT-DETR lineage without re-derivation.
invented entities (3)
  • DBFSAF (Dual-Branch Frequency-Spatial Adaptive Fusion) no independent evidence
    purpose: Diversify and adaptively fuse CNN-ViT features while preserving high-frequency cues via FDConv + partial MKSRU/FPU refinement.
    New composite block; independent evidence is only the ablation gain on the two SOD benchmarks.
  • SFS-FF (Shunt Frequency-Spatial Feature Fusion) no independent evidence
    purpose: Bidirectional cross-scale interaction of spatial, FFT-processed frequency, and residual streams inside the hybrid encoder.
    New fusion operator; value shown only by end-to-end AP improvement.
  • FSD-Down (Frequency-Spatial Dynamic Downsampling) no independent evidence
    purpose: Replace strided conv with learnable wavelet + grouped-conv downsampling that retains high-frequency sub-bands.
    New operator built on HWD ideas; independent evidence limited to ablation and qualitative maps.

pith-pipeline@v1.1.0-grok45 · 25037 in / 2816 out tokens · 25802 ms · 2026-07-11T07:49:07.958387+00:00 · methodology

0 comments
read the original abstract

Small object detection (SOD) remains a challenging task in real-world applications. Despite recent advances, existing detectors remain limited by rigid processing that entangle spatial aggregation with implicit frequency aliasing and truncation, leading to inadequate preservation of high-frequency components for SOD. To tackle these limitations, we propose a Frequency-Spatial Domain Collaborative Detection Transformer (FSDC-DETR), a novel collaborative framework that explicitly models complementary spatial and frequency representations. Specifically, we first introduce Dual-Branch Frequency-Spatial Adaptive Fusion (DBFSAF) to enhance frequency diversity and adaptively capture frequency-spatial domain discriminative representations. Building on these representations, a frequency-spatial interaction scheme is further explored within the hybrid encoder to enable progressive feature propagation to the decoder. In particular, structure-aware frequency-spatial aggregation is achieved through Shunt Frequency-Spatial Feature Fusion (SFS-FF), establishing bidirectional interaction and progressive cross-scale propagation between frequency and spatial representations for coherent discriminative modeling. Meanwhile, informative high-frequency responses are preserved during scale transitions through Frequency-Spatial Dynamic Downsampling (FSD-Down), thereby minimizing frequency degradation throughout multi-scale fusion for the precise SOD. Experimental results demonstrate that FSDC-DETR achieves state-of-the-art performance, improving AP by 6.4 on VisDrone-DET2019 and 6.6 on AITODv2, with gains of 6.8 and 6.9 AP for small objects. The code is available at github.com/nevereverinsomnia/FSDC-DETR.

Figures

Figures reproduced from arXiv: 2607.05176 by Aiwen Liu, Chengguang Zhu, Dandan Zhu, Gang Wang, Haodong Lin, Huiyu Zhou, Yan Wang, Zhengyi Pan.

Figure 1
Figure 1. Figure 1: Frequency response analysis of different backbone architectures. SOD focuses on identifying and localizing objects with extremely limited spatial extent in images [68, 77]. Although spatially limited, these objects play a critical role in real-world applications. The challenges of SOD mainly stem from insufficient feature representation capacity in the model backbone, key in￾formation loss in the deeper la… view at source ↗
Figure 2
Figure 2. Figure 2: Overall architecture of the proposed FSDC-DETR As illustrated in [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Illustration of the Dual-Branch Frequency-Spatial Adaptive Fusion. which provides robust feature representations in various scenarios, and a sim￾ple CNN, enabling complementary representation learning and achieving state￾of-the-art performance in general object detection. However, DEIMv2 combines heterogeneous representations from the ViT and CNN branches via channel-wise concatenation, followed by a 1×1 c… view at source ↗
Figure 4
Figure 4. Figure 4: Illustration of the Shunt Frequency-Spatial Feature Fusion. Most existing hybrid encoders [24, 25, 35, 38, 43, 70, 92] rely on convolution￾based feature fusion and downsampling operations with spatial reduction, which often incur frequency misalignment and attenuate high-frequency components that are essential for SOD. Motivated by this limitation, we revisit the hybrid encoder and propose the Frequency-Sp… view at source ↗
Figure 5
Figure 5. Figure 5: Illustration of the Frequency-Spatial Dynamic Downsampling. ples spatial aggregation with implicit frequency aliasing. Such operations intro￾duce aliasing artifacts and attenuate high-frequency responses that are essential for the precise SOD. UAV-DETR [87] proposed a frequency focused downsam￾pling module that applies average pooling followed by a fast Fourier transform to reduce spatial resolution. Howev… view at source ↗
Figure 6
Figure 6. Figure 6: Visualization comparison of small object detection results on the VisDrone￾DET2019 test split. Orange boxes indicate zoomed-in details. Benefiting from the integration of DBFSAF, SFS-FF, and FSD-Down, FSDC￾DETR demonstrates superior capability in SOD. On the VisDrone-DET2019 test split, FSDC-DETR exhibits more precise localization of small objects, as shown in the first two columns of [PITH_FULL_IMAGE:fig… view at source ↗
Figure 7
Figure 7. Figure 7: Visualization comparison of small object detection results on the AITODv2 test split. Green boxes indicate zoomed-in details. 5 Conclusion In this paper, we present FSDC-DETR for the precise SOD. Unlike conventional detectors that implicitly entangle spatial aggregation with frequency attenua￾tion, FSDC-DETR explicitly constructs, propagates, and preserves frequency￾aware representations throughout the det… view at source ↗

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

89 extracted references · 14 linked inside Pith

  1. [1]

    In: 2021 IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition Workshops (CVPRW)

    Abello, A.A., Hirata, R., Wang, Z.: Dissecting the high-frequency bias in con- volutional neural networks. In: 2021 IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition Workshops (CVPRW). pp. 863–871 (2021).https: //doi.org/10.1109/CVPRW53098.2021.00096

    doi:10.1109/cvprw53098.2021.00096 2021

  2. [2]

    In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

    Bian, J., Feng, M., Dong, W., Wu, F., Luo, J., Wang, Y., Shi, G.: Feature infor- mation driven position gaussian distribution estimation for tiny object detection. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 30376–30386 (2025).https://doi.org/10.1109/CVPR52734.2025. 02828

    doi:10.1109/cvpr52734.2025 2025

  3. [3]

    arXiv preprint arXiv:2511.16719 (2025)

    Carion, N., Gustafson, L., Hu, Y.T., Debnath, S., Hu, R., Suris, D., Ryali, C., Alwala,K.V.,Khedr,H.,Huang,A.,etal.:Sam3:Segmentanythingwithconcepts. arXiv preprint arXiv:2511.16719 (2025)

    Pith/arXiv arXiv 2025

  4. [4]

    In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M

    Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision – ECCV 2020. pp. 213–229. Springer International Publishing, Cham (2020)

    2020

  5. [5]

    In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

    Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV). pp. 9630–9640 (2021). https://doi.org/10.1109/ICCV48922.2021.00951

    doi:10.1109/iccv48922.2021.00951 2021

  6. [6]

    IEEE Transactions on Pattern Analysis and Machine Intelligence46(12), 10763–10780 (2024).https://doi.org/10.1109/ TPAMI.2024.3449959

    Chen, L., Fu, Y., Gu, L., Yan, C., Harada, T., Huang, G.: Frequency-aware feature fusion for dense image prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence46(12), 10763–10780 (2024).https://doi.org/10.1109/ TPAMI.2024.3449959

    arXiv 2024

  7. [7]

    IEEE Transactions on Pattern Analysis and Machine Intelli- gence47(11), 9767–9784 (2025).https://doi.org/10.1109/TPAMI.2025.3592621

    Chen, L., Fu, Y., Gu, L., Zheng, D., Dai, J.: Spatial frequency modulation for se- mantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelli- gence47(11), 9767–9784 (2025).https://doi.org/10.1109/TPAMI.2025.3592621

    doi:10.1109/tpami.2025.3592621 2025

  8. [8]

    In: 2025 IEEE/CVF International Conference on Computer Vision (ICCV)

    Chen,L.,Gu,L.,Fu,Y.:Frequency-dynamicattentionmodulationfordensepredic- tion. In: 2025 IEEE/CVF International Conference on Computer Vision (ICCV). pp. 22620–22632 (2025).https://doi.org/10.1109/ICCV51701.2025.02100

    doi:10.1109/iccv51701.2025.02100 2025

  9. [11]

    IEEE Trans- actions on Pattern Analysis and Machine Intelligence47(6), 4240–4252 (2025)

    Chen, Y., Yuan, X., Wang, J., Wu, R., Li, X., Hou, Q., et al.: Yolo-ms: Rethink- ing multi-scale representation learning for real-time object detection. IEEE Trans- actions on Pattern Analysis and Machine Intelligence47(6), 4240–4252 (2025). https://doi.org/10.1109/TPAMI.2025.3538473

    doi:10.1109/tpami.2025.3538473 2025

  10. [12]

    Cheng, Y., Cao, Y., Yao, H., Luo, W., Jiang, C., Zhang, H., Shen, W.: A comprehensive survey for real-world industrial surface defect detection: Chal- lenges, approaches, and prospects. Journal of Manufacturing Systems84, 152– 172 (2026).https://doi.org/https://doi.org/10.1016/j.jmsy.2025.11.022, https://www.sciencedirect.com/science/article/pii/S02786125...

    doi:10.1016/j.jmsy.2025.11.022 2026

  11. [13]

    IEEE Transactions on Pattern Analysis and Machine Intelligence 48(4), 4167–4183 (2026).https://doi.org/10.1109/TPAMI.2025.3642893

    Cong, R., Chen, Z., Fang, H., Kwong, S., Zhang, W.: Breaking barriers, localizing saliency: A large-scale benchmark and baseline for condition-constrained salient object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 48(4), 4167–4183 (2026).https://doi.org/10.1109/TPAMI.2025.3642893

    doi:10.1109/tpami.2025.3642893 2026

  12. [14]

    arXiv preprint arXiv:2103.05959 (2021)

    Cui, C., Guo, R., Du, Y., He, D., Li, F., Wu, Z., Liu, Q., Wen, S., Huang, J., Hu, X., et al.: Beyond self-supervision: A simple yet effective network distillation alternative to improve backbones. arXiv preprint arXiv:2103.05959 (2021)

    Pith/arXiv arXiv 2021

  13. [15]

    In: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

    Du, D., Zhu, P., Wen, L., Bian, X., Lin, H., Hu, Q., et al.: Visdrone-det2019: The vision meets drone object detection in image challenge results. In: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). pp. 213–226 (2019).https://doi.org/10.1109/ICCVW.2019.00030

    doi:10.1109/iccvw.2019.00030 2019

  14. [16]

    Nature Communications15(1), 1347 (2024)

    Fan, W., Yang, Y., Qi, J., Zhang, Q., Liao, C., Wen, L., et al.: A deep-learning- based framework for identifying and localizing multiple abnormalities and assessing cardiomegaly in chest x-ray. Nature Communications15(1), 1347 (2024)

    2024

  15. [17]

    In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recog- nition (CVPR)

    Ghiasi, G., Cui, Y., Srinivas, A., Qian, R., Lin, T.Y., Cubuk, E.D., Le, Q.V., Zoph, B.: Simple copy-paste is a strong data augmentation method for instance segmen- tation. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recog- nition (CVPR). pp. 2917–2927 (2021).https://doi.org/10.1109/CVPR46437. 2021.00294

    doi:10.1109/cvpr46437 2021

  16. [18]

    In: 2015 IEEE International Conference on Computer Vision (ICCV)

    Girshick, R.: Fast r-cnn. In: 2015 IEEE International Conference on Computer Vision (ICCV). pp. 1440–1448 (2015).https://doi.org/10.1109/ICCV.2015.169

    doi:10.1109/iccv.2015.169 2015

  17. [19]

    Pearson Education India (2009)

    Gonzalez, R.C.: Digital image processing. Pearson Education India (2009)

    2009

  18. [20]

    In: Proceedings of the 35th International Conference on Neural Information Processing Systems

    He, J., Erfani, S., Ma, X., Bailey, J., Chi, Y., Hua, X.S.: Alpha-iou: a family of power intersection over union losses for bounding box regression. In: Proceedings of the 35th International Conference on Neural Information Processing Systems. NIPS ’21, Curran Associates Inc., Red Hook, NY, USA (2021)

    2021

  19. [21]

    IEEE Transactions on Geoscience and Remote Sensing63, 1–19 (2025)

    Hu, L., Yuan, J., Cheng, B., Xu, Q.: Csfpr-rtdetr: Real-time small object detec- tion network for uav images based on cross-spatial-frequency domain and position relation. IEEE Transactions on Geoscience and Remote Sensing63, 1–19 (2025). https://doi.org/10.1109/TGRS.2025.3601828

    doi:10.1109/tgrs.2025.3601828 2025

  20. [22]

    Artificial Intelligence Review58(6), 162 (2025)

    Hua, W., Chen, Q.: A survey of small object detection based on deep learning in aerial images. Artificial Intelligence Review58(6), 162 (2025)

    2025

  21. [23]

    arXiv preprint arXiv:2502.01303 (2025)

    Huang, H., Xia, T., Ren, P., et al.: Partial channel network: Compute fewer, per- form better. arXiv preprint arXiv:2502.01303 (2025)

    Pith/arXiv arXiv 2025

  22. [24]

    arXiv preprint arXiv:2509.20787 (2025)

    Huang, S., Hou, Y., Liu, L., Yu, X., Shen, X.: Real-time object detection meets dinov3. arXiv preprint arXiv:2509.20787 (2025)

    arXiv 2025

  23. [25]

    In: 2025 IEEE/CVF Conference on Com- puter Vision and Pattern Recognition (CVPR)

    Huang, S., Lu, Z., Cun, X., Yu, Y., Zhou, X., Shen, X.: Deim: Detr with im- proved matching for fast convergence. In: 2025 IEEE/CVF Conference on Com- puter Vision and Pattern Recognition (CVPR). pp. 15162–15171 (2025).https: //doi.org/10.1109/CVPR52734.2025.01412

    doi:10.1109/cvpr52734.2025.01412 2025

  24. [26]

    In: 2023 IEEE/CVF International Conference on Computer Vision (ICCV)

    Huang, Z., Zhang, Z., Lan, C., Zha, Z.J., Lu, Y., Guo, B.: Adaptive frequency fil- ters as efficient global token mixers. In: 2023 IEEE/CVF International Conference on Computer Vision (ICCV). pp. 6026–6036 (2023).https://doi.org/10.1109/ ICCV51070.2023.00556

    arXiv 2023

  25. [27]

    arXiv preprint arXiv:2407.20892 (2024)

    Khanam, R., Hussain, M.: What is yolov5: A deep look into the internal features of the popular object detector. arXiv preprint arXiv:2407.20892 (2024)

    Pith/arXiv arXiv 2024

  26. [28]

    arXiv preprint arXiv:2410.17725 (2024)

    Khanam, R., Hussain, M.: Yolov11: An overview of the key architectural enhance- ments. arXiv preprint arXiv:2410.17725 (2024)

    Pith/arXiv arXiv 2024

  27. [29]

    arXiv preprint arXiv:2506.17733 (2025) 18 Liu et al

    Lei, M., Li, S., Wu, Y., Hu, H., Zhou, Y., Zheng, X., Ding, G., Du, S., Wu, Z., Gao, Y.: Yolov13: Real-time object detection with hypergraph-enhanced adaptive visual perception. arXiv preprint arXiv:2506.17733 (2025) 18 Liu et al

    Pith/arXiv arXiv 2025

  28. [30]

    In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

    Li, F., Zeng, A., Liu, S., Zhang, H., Li, H., Zhang, L., et al.: Lite detr : An in- terleaved multi-scale encoder for efficient detr. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 18558–18567 (2023). https://doi.org/10.1109/CVPR52729.2023.01780

    doi:10.1109/cvpr52729.2023.01780 2023

  29. [31]

    In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

    Li, H., Wu, Z., Shao, R., Zhang, T., Fu, Y.: Noise calibration and spatial-frequency interactive network for stem image enhancement. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 21287–21296 (2025). https://doi.org/10.1109/CVPR52734.2025.01983

    doi:10.1109/cvpr52734.2025.01983 2025

  30. [32]

    In: 2025 IEEE/CVF International Con- ference on Computer Vision (ICCV)

    Li, J., Wu, H., Qin, J.: Weaveseg: Iterative contrast-weaving and spectral feature- refining for nuclei instance segmentation. In: 2025 IEEE/CVF International Con- ference on Computer Vision (ICCV). pp. 21984–21993 (2025).https://doi.org/ 10.1109/ICCV51701.2025.02041

    doi:10.1109/iccv51701.2025.02041 2025

  31. [33]

    In: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

    Li, K., Wang, D., Hu, Z., Zhu, W., Li, S., Wang, Q.: Unleashing channel potential: Space-frequency selection convolution for sar object detection. In: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 17323– 17332 (2024).https://doi.org/10.1109/CVPR52733.2024.01640

    doi:10.1109/cvpr52733.2024.01640 2024

  32. [34]

    In: 2023 IEEE/CVF International Conference on Computer Vision (ICCV)

    Li, Y., Hou, Q., Zheng, Z., Cheng, M.M., Yang, J., Li, X.: Large selective kernel network for remote sensing object detection. In: 2023 IEEE/CVF International Conference on Computer Vision (ICCV). pp. 16748–16759 (2023).https://doi. org/10.1109/ICCV51070.2023.01540

    doi:10.1109/iccv51070.2023.01540 2023

  33. [35]

    arXiv preprint arXiv:2510.25257 (2025)

    Liao, Z., Zhao, Y., Shan, X., Yan, Y., Liu, C., Lu, L., Ji, X., Chen, J.: Rt-detrv4: Painlessly furthering real-time object detection with vision foundation models. arXiv preprint arXiv:2510.25257 (2025)

    arXiv 2025

  34. [36]

    In: Proceedings of the 33rd ACM International Conference on Multimedia

    Liu, H., Jia, C., Shi, F., Cheng, X., Shi, M., Xie, X., et al.: Lidar: Lightweight adaptive cue-aware fusion vision mamba for multimodal segmentation of structural cracks. In: Proceedings of the 33rd ACM International Conference on Multimedia. p. 1832–1841. MM ’25, Association for Computing Machinery, New York, NY, USA (2025).https://doi.org/10.1145/37460...

    doi:10.1145/3746027.3755452 2025

  35. [37]

    Expert Systems with Applications263, 125727 (2025).https://doi.org/https: //doi.org/10.1016/j.eswa.2024.125727,https://www.sciencedirect.com/ science/article/pii/S0957417424025946

    Lv,S.,Liang,T.,Zhang,K.,Jiang,S.,Ouyang,B.,Li,Q.,Li,X.:Alightweighthier- archical aggregation task alignment network for industrial surface defect detection. Expert Systems with Applications263, 125727 (2025).https://doi.org/https: //doi.org/10.1016/j.eswa.2024.125727,https://www.sciencedirect.com/ science/article/pii/S0957417424025946

    doi:10.1016/j.eswa.2024.125727 2025

  36. [38]

    arXiv preprint arXiv:2407.17140 (2024)

    Lv, W., Zhao, Y., Chang, Q., Huang, K., Wang, G., Liu, Y.: Rt-detrv2: Improved baseline with bag-of-freebies for real-time detection transformer. arXiv preprint arXiv:2407.17140 (2024)

    Pith/arXiv arXiv 2024

  37. [39]

    In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

    Meng, D., Chen, X., Fan, Z., Zeng, G., Li, H., Yuan, Y., et al.: Conditional detr for fast training convergence. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV). pp. 3631–3640 (2021).https://doi.org/10.1109/ ICCV48922.2021.00363

    arXiv 2021

  38. [40]

    arXiv preprint arXiv:2304.07193 (2023)

    Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., et al.: Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)

    Pith/arXiv arXiv 2023

  39. [41]

    Park, N., Kim, S.: How do vision transformers work? arXiv preprint arXiv:2202.06709 (2022)

    Pith/arXiv arXiv 2022

  40. [42]

    In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)

    Paul, S., Chen, P.Y.: Vision transformers are robust learners. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). vol. 36, pp. 2071–2081 (2022)

    2071

  41. [43]

    In: International Conference on Learning Representations

    Peng, Y., Li, H., Wu, P., Zhang, Y., Sun, X., Wu, F.: D-fine: Redefine regression task of detrs as fine-grained distribution refinement. In: International Conference on Learning Representations. vol. 2025, pp. 44015–44031 (2025) FSDC-DETR 19

    2025

  42. [44]

    John Wiley & Sons (2000)

    Pitas, I.: Digital image processing algorithms and applications. John Wiley & Sons (2000)

    2000

  43. [45]

    In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

    Qin, Z., Zhang, P., Wu, F., Li, X.: Fcanet: Frequency channel attention networks. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV). pp. 763–772 (2021).https://doi.org/10.1109/ICCV48922.2021.00082

    doi:10.1109/iccv48922.2021.00082 2021

  44. [46]

    In: 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

    Rahman, M.M., Marculescu, R.: Mk-unet: Multi-kernel lightweight cnn for medical image segmentation. In: 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). pp. 1053–1062 (2025).https://doi.org/10.1109/ ICCVW69036.2025.00114

    arXiv 2025

  45. [47]

    arXiv preprint arXiv:2601.17237 (2026)

    Ranzinger, M., Heinrich, G., McCarthy, C., Kautz, J., Tao, A., Catanzaro, B., Molchanov, P.: C-radiov4 (tech report). arXiv preprint arXiv:2601.17237 (2026)

    arXiv 2026

  46. [48]

    Ren, K., Li, Z., Du, Y., Han, H., Wu, Y.: Fii-detr: Few-shot object detection with fully information interaction. Inf. Fusion127(PA) (Jun 2026).https://doi.org/ 10.1016/j.inffus.2025.103728,https://doi.org/10.1016/j.inffus.2025. 103728

    doi:10.1016/j.inffus.2025.103728 2026

  47. [50]

    arXiv preprint arXiv:2511.09554 (2025)

    Robinson, I., Robicheaux, P., Popov, M., Ramanan, D., Peri, N.: Rf-detr: neural architecture search for real-time detection transformers. arXiv preprint arXiv:2511.09554 (2025)

    arXiv 2025

  48. [51]

    arXiv preprint arXiv:2509.25164 (2025)

    Sapkota, R., Cheppally, R.H., Sharda, A., Karkee, M.: Yolo26: key architectural enhancements and performance benchmarking for real-time object detection. arXiv preprint arXiv:2509.25164 (2025)

    arXiv 2025

  49. [52]

    Information Fusion126, 103575 (2026).https: //doi.org/https://doi.org/10.1016/j.inffus.2025.103575,https://www

    Sapkota, R., Karkee, M.: Object detection with multimodal large vision-language models: An in-depth review. Information Fusion126, 103575 (2026).https: //doi.org/https://doi.org/10.1016/j.inffus.2025.103575,https://www. sciencedirect.com/science/article/pii/S1566253525006475

    doi:10.1016/j.inffus.2025.103575 2026

  50. [54]

    Shi, Z., Hu, J., Ren, J., Ye, H., Yuan, X., Ouyang, Y., He, J., Ji, B., Guo, J.: Hs-fpn: high frequency and spatial perception fpn for tiny object detection. In: Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelli- gence and Fifteenth Symposium on Educati...

    doi:10.1609/aaai.v39i7.32740 2025

  51. [55]

    arXiv preprint arXiv:2601.08602 (2026)

    Shu, Z., Wu, J., Yan, W., Liu, X., Zhang, H., Liu, C., Mao, Y., Chen, J.: Wave- former: Frequency-time decoupled vision modeling with wave equation. arXiv preprint arXiv:2601.08602 (2026)

    arXiv 2026

  52. [56]

    arXiv preprint arXiv:2508.10104 (2025)

    Siméoni, O., Vo, H.V., Seitzer, M., Baldassarre, F., Oquab, M., Jose, C., et al.: Dinov3. arXiv preprint arXiv:2508.10104 (2025)

    Pith/arXiv arXiv 2025

  53. [57]

    IEEE Transactions on Image Pro- cessing34, 7684–7696 (2025).https://doi.org/10.1109/TIP.2025.3632221 20 Liu et al

    Sun, H., Lv, L., Zhang, P., Tang, T., Tian, F., Sun, W., Lu, H.: Spatial-frequency enhanced mamba for multi-modal image fusion. IEEE Transactions on Image Pro- cessing34, 7684–7696 (2025).https://doi.org/10.1109/TIP.2025.3632221 20 Liu et al

    doi:10.1109/tip.2025.3632221 2025

  54. [58]

    In: 2025 IEEE/CVF Conference on Com- puter Vision and Pattern Recognition (CVPR)

    Sun, H., Wang, R., Li, Y., Yang, L., Lin, S., Cao, X., Zhang, B.: Set: Spectral enhancement for tiny object detection. In: 2025 IEEE/CVF Conference on Com- puter Vision and Pattern Recognition (CVPR). pp. 4713–4723 (2025).https: //doi.org/10.1109/CVPR52734.2025.00444

    doi:10.1109/cvpr52734.2025.00444 2025

  55. [59]

    In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G

    Sun, Y., Xu, C., Yang, J., Xuan, H., Luo, L.: Frequency-spatial entanglement learning for camouflaged object detection. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision – ECCV 2024. pp. 343–360. Springer Nature Switzerland, Cham (2025)

    2024

  56. [60]

    Tatsunami, Y., Taki, M.: Fft-based dynamic token mixer for vision. In: Pro- ceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence. AAAI’24/IAAI’24/EAAI’24, AAAI Press (2024).https:...

    doi:10.1609/aaai.v38i14.29457 2024

  57. [61]

    In: Belgrave, D., Zhang, C., Lin, H., Pascanu, R., Koniusz, P., Ghassemi, M., Chen, N

    Tian, Y., Ye, Q., Doermann, D.: Yolov12: Attention-centric real-time object detec- tors. In: Belgrave, D., Zhang, C., Lin, H., Pascanu, R., Koniusz, P., Ghassemi, M., Chen, N. (eds.) Advances in Neural Information Processing Systems. vol. 38, pp. 78433–78457. Curran Associates, Inc. (2025),https://proceedings.neurips.cc/ paper _ files / paper / 2025 / fil...

    2025

  58. [62]

    arXiv preprint arXiv:2301.10051 (2023)

    Tong, Z., Chen, Y., Xu, Z., Yu, R.: Wise-iou: bounding box regression loss with dynamic focusing mechanism. arXiv preprint arXiv:2301.10051 (2023)

    Pith/arXiv arXiv 2023

  59. [63]

    In: 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS)

    Varghese, R., M., S.: Yolov8: A novel object detection algorithm with enhanced performance and robustness. In: 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS). pp. 1–6 (2024). https://doi.org/10.1109/ADICS58448.2024.10533619

    doi:10.1109/adics58448.2024.10533619 2024

  60. [64]

    In: Proceedings of the 38th International Conference on Neural Information Processing Systems

    Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., et al.: Yolov10: real-time end-to-end object detection. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. NIPS ’24, Curran Associates Inc., Red Hook, NY, USA (2024)

    2024

  61. [65]

    In: 2025 IEEE/CVF International Conference on Computer Vision (ICCV)

    Wang, A., Liu, L., Chen, H., Lin, Z., Han, J., Ding, G.: Yoloe: Real-time seeing any- thing. In: 2025 IEEE/CVF International Conference on Computer Vision (ICCV). pp. 24591–24602 (2025).https://doi.org/10.1109/ICCV51701.2025.02280

    doi:10.1109/iccv51701.2025.02280 2025

  62. [66]

    In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G

    Wang, C.Y., Yeh, I.H., Mark Liao, H.Y.: Yolov9: Learning what you want to learn using programmable gradient information. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision – ECCV 2024. pp. 1–21. Springer Nature Switzerland, Cham (2025)

    2024

  63. [67]

    In: 2020 IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition (CVPR)

    Wang, H., Wu, X., Huang, Z., Xing, E.P.: High-frequency component helps explain the generalization of convolutional neural networks. In: 2020 IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition (CVPR). pp. 8681–8691 (2020). https://doi.org/10.1109/CVPR42600.2020.00871

    doi:10.1109/cvpr42600.2020.00871 2020

  64. [68]

    In: 2020 25th International Conference on Pattern Recognition (ICPR)

    Wang, J., Yang, W., Guo, H., Zhang, R., Xia, G.S.: Tiny object detection in aerial images. In: 2020 25th International Conference on Pattern Recognition (ICPR). pp. 3791–3798 (2021).https://doi.org/10.1109/ICPR48806.2021.9413340

    doi:10.1109/icpr48806.2021.9413340 2020

  65. [69]

    arXiv preprint arXiv:2203.05962 (2022)

    Wang, P., Zheng, W., Chen, T., Wang, Z.: Anti-oversmoothing in deep vision trans- formers via the fourier domain analysis: From theory to practice. arXiv preprint arXiv:2203.05962 (2022)

    Pith/arXiv arXiv 2022

  66. [70]

    In: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

    Wang, S., Xia, C., Lv, F., Shi, Y.: Rt-detrv3: Real-time end-to-end object de- tection with hierarchical dense positive supervision. In: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). pp. 1628–1636 (2025). https://doi.org/10.1109/WACV61041.2025.00166 FSDC-DETR 21

    doi:10.1109/wacv61041.2025.00166 2025

  67. [71]

    In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recog- nition (CVPR)

    Wang, Y., Wang, H., Wang, L., Wang, X., Zhu, L., Lu, W., et al.: Complementary advantages: Exploiting cross-field frequency correlation for nir-assisted image de- noising. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recog- nition (CVPR). pp. 12679–12689 (2025).https://doi.org/10.1109/CVPR52734. 2025.01183

    doi:10.1109/cvpr52734 2025

  68. [72]

    Wang, Z., Li, C., Xu, H., Zhu, X., Li, H.: Mamba yolo: a simple baseline for ob- ject detection with state space model. In: Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innova- tive Applications of Artificial Intelligence and Fifteenth Symposium on Educa- tional Advances in Artificial Intellig...

    doi:10.1609/aaai.v39i8.32885 2025

  69. [73]

    Medical Image Analysis109, 103906 (2026).https: //doi.org/https://doi.org/10.1016/j.media.2025.103906,https://www

    Wei, J., Li, Y., Fan, X., Ma, W., Qiu, M., Chen, H., Lei, W.: Sam-swin: Sam- driven dual-swin transformers with adaptive lesion enhancement for laryngo- pharyngeal tumor detection. Medical Image Analysis109, 103906 (2026).https: //doi.org/https://doi.org/10.1016/j.media.2025.103906,https://www. sciencedirect.com/science/article/pii/S1361841525004529

    doi:10.1016/j.media.2025.103906 2026

  70. [74]

    arXiv preprint arXiv:2504.15165 (2025)

    Wenbin, L.: An efficient aerial image detection with variable receptive fields. arXiv preprint arXiv:2504.15165 (2025)

    Pith/arXiv arXiv 2025

  71. [75]

    IEEE Transactions on Pattern Analysis and Machine Intelligence48(7), 7467–7484 (2026).https://doi.org/10.1109/TPAMI

    Xia, Q., zheng, L., Zhao, S., Huang, X., Wu, H., Wen, C., Wang, C.: Dota++: Unsupervisely and collaboratively detect objects from multi-agent observations with multi-modal prior constraints. IEEE Transactions on Pattern Analysis and Machine Intelligence48(7), 7467–7484 (2026).https://doi.org/10.1109/TPAMI. 2026.3664863

    doi:10.1109/tpami 2026

  72. [76]

    In: Proceedings of the AAAI Conference on Artificial Intelligence

    Xiao, Y., Xu, T., Xin, Y., Li, J.: Fbrt-yolo: Faster and better for real-time aerial image detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 39, pp. 8673–8681 (2025)

    2025

  73. [77]

    ISPRS Journal of Photogrammetry and Remote Sensing190, 79–93 (2022).https:// doi.org/https://doi.org/10.1016/j.isprsjprs.2022.06.002,https://www

    Xu, C., Wang, J., Yang, W., Yu, H., Yu, L., Xia, G.S.: Detecting tiny objects in aerial images: A normalized wasserstein distance and a new benchmark. ISPRS Journal of Photogrammetry and Remote Sensing190, 79–93 (2022).https:// doi.org/https://doi.org/10.1016/j.isprsjprs.2022.06.002,https://www. sciencedirect.com/science/article/pii/S0924271622001599

    doi:10.1016/j.isprsjprs.2022.06.002 2022

  74. [78]

    Pattern Recognition143, 109819 (2023).https://doi.org/https://doi.org/10.1016/j

    Xu, G., Liao, W., Zhang, X., Li, C., He, X., Wu, X.: Haar wavelet downsampling: A simple but effective downsampling module for semantic segmentation. Pattern Recognition143, 109819 (2023).https://doi.org/https://doi.org/10.1016/j. patcog.2023.109819,https://www.sciencedirect.com/science/article/pii/ S0031320323005174

    doi:10.1016/j 2023

  75. [79]

    In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

    Yan, F., Jiang, X., Lu, Y., Cao, J., Chen, D., Xu, M.: Wavelet and prototype aug- mented query-based transformer for pixel-level surface defect detection. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 23860–23869 (2025).https://doi.org/10.1109/CVPR52734.2025.02222

    doi:10.1109/cvpr52734.2025.02222 2025

  76. [80]

    In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

    Yang, C., Huang, Z., Wang, N.: Querydet: Cascaded sparse query for accel- erating high-resolution small object detection. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 13658–13667 (2022). https://doi.org/10.1109/CVPR52688.2022.01330

    doi:10.1109/cvpr52688.2022.01330 2022

  77. [81]

    Yang, J., Liu, S., Wu, J., Su, X., Hai, N., Huang, X.: Pinwheel-shaped con- volution and scale-based dynamic loss for infrared small target detection. In: Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteenth Symposium on Educational Adva...

    doi:10.1609/aaai.v39i9.32996 2025

  78. [82]

    In: Proceedings of the 33rd International Conference on Neural Information Processing Systems

    Yin, D., Lopes, R.G., Shlens, J., Cubuk, E.D., Gilmer, J.: A fourier perspective on model robustness in computer vision. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA (2019)

    2019

  79. [83]

    Pattern Recogni- tion148, 110152 (2024).https : / / doi

    Zhan, J., Luo, Y., Guo, C., Wu, Y., Meng, J., Liu, J.: Yolopx: Anchor-free multi-task learning network for panoptic driving perception. Pattern Recogni- tion148, 110152 (2024).https : / / doi . org / https : / / doi . org / 10 . 1016 / j . patcog.2023.110152,https://www.sciencedirect.com/science/article/pii/ S003132032300849X

    arXiv 2024

  80. [84]

    detr: Instructive multi-route training for detection transformers

    Zhang, C.B., Zhong, Y., Han, K.: Mr. detr: Instructive multi-route training for detection transformers. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 9933–9943 (2025).https://doi.org/10.1109/ CVPR52734.2025.00928

    arXiv 2025

Showing first 80 references.