Pith. sign in

REVIEW 3 major objections 5 minor 37 references

Text prompts that modulate transformer queries improve oriented object detection in aerial images.

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

2026-07-10 13:52 UTC pith:BTET3VVH

load-bearing objection Solid SOTA numbers on DOTA via language-conditioned oriented DETR, but the gains rest on an unablated perfect-prompt protocol that no pure-vision baseline receives. the 3 major comments →

arxiv 2607.08004 v1 pith:BTET3VVH submitted 2026-07-09 cs.CV

LOGOS: Language-guided Oriented Object Detection in Aerial Scenes

Trong-Thuan Nguyen , Minh-Triet Tran This is my paper
classification cs.CV
keywords oriented object detectionaerial imagerytransformerslanguage guidanceprompt modulationremote sensingDOTA
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.

Detecting ships, vehicles, and buildings in satellite and drone imagery is hard because objects appear at arbitrary angles, pack densely, and sit in cluttered backgrounds. Prior detectors struggle with fixed numbers of queries, angular discontinuity, and ambiguity for square-like boxes. LOGOS conditions a transformer detector on a short textual prompt that names the categories present in the image. The prompt modulates the content queries and is attended to jointly with visual features, so the model focuses only on the named objects. On the DOTA benchmarks the method reports higher mean average precision than previous oriented detectors, with the largest gains in crowded harbors and rotated scenes.

Core claim

Conditioning a DETR-style oriented detector on a textual prompt that lists the object categories present in an aerial image, via FiLM-modulated content queries and text-aware cross-attention, yields higher mean average precision than prior oriented detectors on DOTA-v1.0, v1.5 and v2.0, especially for densely packed and rotated objects.

What carries the argument

Prompt-modulated content queries: learnable queries are FiLM-conditioned by a pooled text embedding of the prompt, then attend jointly to visual tokens and text tokens; angle is encoded as (sin θ, cos θ) and a class mask zeros logits outside the prompt’s categories.

Load-bearing premise

The textual prompt given at both train and test time is exactly the set of ground-truth categories that appear in the image, so the class mask and query modulation never see missing or extra labels.

What would settle it

Re-run the DOTA evaluation with prompts that omit some present categories or add absent ones; if mAP falls to or below the strongest non-language baselines, the reported gains depend on oracle-category prompts.

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

If this is right

  • Oriented detectors can trade fixed query budgets for language-conditioned query selection, reducing wasted computation on empty regions.
  • Angular discontinuity can be mitigated by (sin, cos) regression plus language-guided class masking without specialized angle classification heads.
  • The same prompt interface can be reused for sparse versus dense aerial scenes simply by changing the text, without retraining separate models.
  • Applications such as harbor monitoring or urban inventory can filter detections to user-specified categories at inference time.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the prompt is allowed to be free-form natural language rather than an exact category list, the same architecture becomes a candidate open-vocabulary oriented detector for remote sensing.
  • The failure cases of extreme density and unusual orientations suggest that prompt modulation alone may still need denser multi-scale sampling or orientation-equivariant backbones.
  • Because the method already injects text into every decoder layer, adding multi-spectral or SAR tokens would be a natural next multi-modal extension.

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

3 major / 5 minor

Summary. The paper proposes LOGOS, a DETR/DINO-style transformer for oriented object detection in aerial imagery that conditions detection on a textual prompt. Content queries are modulated via FiLM using a pooled prompt embedding (Eq. 2), text-aware multi-head cross-attention attends jointly to visual and text tokens (Eq. 3), angles are encoded with sine/cosine, and a hard class mask derived from the prompt zeros out irrelevant logits (Eq. 4). The model is trained with a standard DETR-style combination of classification, L1, RotGIoU and contrastive denoising losses, and is evaluated on DOTA-v1.0/1.5/2.0 under a ResNet-50 backbone, reporting mAP of 81.32 %, 69.97 % and 66.04 % respectively and claiming state-of-the-art performance especially in dense/rotated scenes.

Significance. If the language-guidance mechanism is genuinely responsible for the gains, the work would constitute a useful step toward open-vocabulary or promptable oriented detection in remote sensing, an application domain where category lists are often known a priori and where angular discontinuity and density variation remain open problems. The numerical results under a common backbone are competitive with recent published detectors, the architecture is described with explicit equations, and the sine-cosine angle encoding plus RotGIoU matching are sensible engineering choices. The absence of any isolation of the language components, however, currently prevents the community from assessing whether the contribution is the claimed prompt modulation or simply a stronger decoder plus an oracle class filter.

major comments (3)
  1. Sec. 5.1 Setup and Eqs. (2)–(4): the evaluation protocol supplies, at both train and test time, a prompt that enumerates exactly the ground-truth categories present in the image; this prompt is used both for FiLM modulation of the content queries and for the hard class mask that sets all other logits to −∞. Every baseline in Tables 1–3 is a pure visual detector that receives no category list. Consequently the reported mAP gains cannot be attributed to language guidance versus an oracle class filter plus a DINO-style decoder. A matched ablation that (a) removes FiLM/mask while keeping the identical decoder and training recipe, and (b) evaluates incomplete or open-vocabulary prompts, is required to establish the central claim.
  2. Tables 1–3: no error bars, no multiple random seeds, and no statistical significance test are provided for the 0.45–8.76-point mAP margins over the strongest prior methods. Given that early-stopping, learning-rate schedule and the precise 900-query configuration are free parameters (Sec. 5.1), the numerical superiority is currently under-supported.
  3. Sec. 4.1–4.3: the paper asserts that prompt-modulated queries solve the fixed-query-size problem of DETR-style models, yet the implementation still uses a fixed 900 decoder queries (explicitly matched to DN-DETR). No experiment varies query count with or without the prompt, so the claimed advantage remains untested.
minor comments (5)
  1. Keywords and abstract contain the typo “Vision-Lanague Models”; correct to “Language”.
  2. Fig. 2 caption and several figure references say “Best viewed in color and zoomed in” but the PDF does not embed high-resolution versions; supply vector or higher-dpi figures.
  3. Eq. (6) uses RotGIoU while the surrounding text sometimes writes “GIoU for oriented bounding boxes”; make the notation consistent.
  4. Sec. 2.3 claims that earlier methods are limited to a 0–90° angular range; several cited works (e.g., CSL, GWD) already address full-periodicity; the discussion should be more precise.
  5. Table 2 reports a “CC” category that is never defined in the text or in the DOTA-v1.5 description given in Sec. 5.1; clarify.

Circularity Check

0 steps flagged

No circularity: empirical architecture + external DOTA benchmarks; SOTA mAPs are measured outcomes, not forced by definition or self-fit.

full rationale

LOGOS is an engineering paper that defines a DETR/DINO-style encoder-decoder, modulates content queries by FiLM on a text prompt (Eq. 2), performs text-aware cross-attention (Eq. 3), applies a hard class mask derived from the same prompt (Eq. 4), and trains with standard Hungarian + CDN losses. The claimed results are simply the mAP numbers obtained by running this model on the public DOTA-v1.0/1.5/2.0 splits and comparing against previously published detectors (Tables 1-3). Nothing in the derivation chain reduces a 'prediction' to an input by construction: there is no parameter fitted on a subset and then re-reported as a prediction, no uniqueness theorem imported from the authors' own prior work, no ansatz smuggled via self-citation, and no algebraic identity that makes the reported mAPs tautological. Citations to DETR, DINO, Deformable DETR, etc., are to independent external foundations. The evaluation protocol (prompt = exact ground-truth category list) is a design choice that may inflate absolute numbers relative to open-vocabulary settings, but that is an experimental-validity concern, not circularity. The paper is therefore self-contained against external benchmarks and scores 0.

Axiom & Free-Parameter Ledger

3 free parameters · 3 axioms · 1 invented entities

The central claim rests on standard transformer and detection assumptions plus a few engineering choices (FiLM, sine-cosine angle, perfect category prompts) that are not independently validated outside this paper.

free parameters (3)
  • loss coefficients (λ_cls=1, λ_L1=5, λ_GIoU=2)
    Hand-chosen weights that balance classification and box regression; different values would change the reported mAP.
  • number of decoder queries (900)
    Fixed to match DN-DETR parity; not derived from data density.
  • learning-rate schedule and early-stopping epoch
    Chosen by hand for the 12/24/36-epoch regimes.
axioms (3)
  • domain assumption Bipartite Hungarian matching with L1 + RotGIoU + focal loss yields a valid set-prediction objective for oriented boxes.
    Inherited from DETR/DINO literature and used without re-derivation (Eqs. 5–6).
  • domain assumption Sine/cosine encoding of θ removes angular discontinuity.
    Standard practice in oriented detection; assumed sufficient (Sec. 4.2).
  • ad hoc to paper The text prompt always enumerates exactly the categories present in the image.
    Stated in Sec. 5.1 Setup; required for the class mask and FiLM to function as described.
invented entities (1)
  • prompt-modulated content queries (FiLM on learnable queries) no independent evidence
    purpose: Condition decoder queries on text so the model focuses only on named categories.
    The specific FiLM application to oriented DETR queries is introduced here; no external evidence of its necessity is given beyond the DOTA numbers.

pith-pipeline@v1.1.0-grok45 · 19181 in / 2432 out tokens · 20709 ms · 2026-07-10T13:52:21.024958+00:00 · methodology

0 comments
read the original abstract

Object detection in geospatial scenes, such as satellite and aerial imagery, poses significant challenges due to the varying orientations and densities of objects, as well as the complex backgrounds inherent to remote sensing imagery. Traditional methods for oriented object detection have struggled to address issues such as angular discontinuity, fixed query sizes, and inefficiencies in handling sparse or cluttered scenes. In this paper, we propose LOGOS, a novel transformer-based approach that leverages textual prompts to guide the detection of oriented objects in aerial scenes. In particular, our proposed approach incorporates prompt-modulated content queries to dynamically adjust the model's focus based on the provided text, thereby improving object detection accuracy in complex environments. Empirically, extensive experiments on the DOTA dataset demonstrate that LOGOS outperforms existing state-of-the-art methods, particularly in densely packed and rotated object scenarios. Our approach offers a significant step forward in improving the robustness and scalability of oriented object detection in remote sensing applications.

Figures

Figures reproduced from arXiv: 2607.08004 by Minh-Triet Tran, Trong-Thuan Nguyen.

Figure 1
Figure 1. Figure 1: Illustration of our approach, where textual [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: An overview of LOGOS, which is a language-guided approach for oriented [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Qualitative results on DOTA. Best viewed in color and zoomed in. buildings, and roundabouts, as evidenced by the purple bounding boxes. In addition, the precision of our proposed approach in handling diverse object scales, orientations, and environmental settings highlights its potential applications in areas such as urban planning, surveillance, and automated navigation. Moreover, [PITH_FULL_IMAGE:figure… view at source ↗
Figure 4
Figure 4. Figure 4: Illustration of failure cases. Best viewed in color and zoomed in. Although our proposed approach has shown promising results, several avenues for future research remain to be explored. One potential direction is to enhance the model’s ability to handle objects at extreme orientations, as the current approach may still face challenges with objects near 0 or 180 degrees, particularly in dense scenes. Additi… view at source ↗

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

37 extracted references · 37 canonical work pages · 5 internal anchors

  1. [1]

    In: European conference on computer vision

    Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End- to-end object detection with transformers. In: European conference on computer vision. pp. 213–229. Springer (2020) 2, 3, 4, 5, 7

    work page 2020

  2. [2]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Chen, K., Pang, J., Wang, J., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Shi, J., Ouyang, W., et al.: Hybrid task cascade for instance segmentation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 4974–4983 (2019) 9, 10

    work page 2019

  3. [3]

    IEEE Transactions on Circuits and Systems for Video Technology (2022) 2, 4, 8, 9

    Dai, L., Liu, H., Tang, H., Wu, Z., Song, P.: Ao2-detr: Arbitrary-oriented object detection transformer. IEEE Transactions on Circuits and Systems for Video Technology (2022) 2, 4, 8, 9

    work page 2022

  4. [4]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Dai, Z., Cai, B., Lin, Y., Chen, J.: Up-detr: Unsupervised pre-training for object detection with transformers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 1601–1610 (2021) 3

    work page 2021

  5. [5]

    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 44(4) (2022) 10

    Detector, A.F.O.: Fcos: A simple and strong anchor-free object detector. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 44(4) (2022) 10

    work page 2022

  6. [6]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Ding, J., Xue, N., Long, Y., Xia, G.S., Lu, Q.: Learning roi transformer for oriented object detection in aerial images. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 2849–2858 (2019) 8, 9, 10

    work page 2019

  7. [7]

    IEEE transactions on pattern analysis and machine intelligence44(11), 7778–7796 (2021) 2, 8

    Ding, J., Xue, N., Xia, G.S., Bai, X., Yang, W., Yang, M.Y., Belongie, S., Luo, J., Datcu, M., Pelillo, M., et al.: Object detection in aerial images: A large-scale benchmark and challenges. IEEE transactions on pattern analysis and machine intelligence44(11), 7778–7796 (2021) 2, 8

    work page 2021

  8. [8]

    IEEE Transactions on Circuits and Systems for Video Technology32(8), 5252–5265 (2022) 8

    Guo, Z., Zhang, X., Liu, C., Ji, X., Jiao, J., Ye, Q.: Convex-hull feature adaptation for oriented and densely packed object detection. IEEE Transactions on Circuits and Systems for Video Technology32(8), 5252–5265 (2022) 8

    work page 2022

  9. [9]

    IEEE Transactions on Geoscience and Remote Sensing60, 1–11 (2021) 8, 10

    Han, J., Ding, J., Li, J., Xia, G.S.: Align deep features for oriented object detection. IEEE Transactions on Geoscience and Remote Sensing60, 1–11 (2021) 8, 10

    work page 2021

  10. [10]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Han, J., Ding, J., Xue, N., Xia, G.S.: Redet: A rotation-equivariant detector for aerial object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 2786–2795 (2021) 8, 9

    work page 2021

  11. [11]

    In: Proceedings of the IEEE international conference on computer vision

    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision. pp. 2961–2969 (2017) 9, 10

    work page 2017

  12. [12]

    In: Proceedings of the AAAI Conference on Artificial Intelligence

    Hou, L., Lu, K., Xue, J., Li, Y.: Shape-adaptive selection and measurement for oriented object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 36, pp. 923–932 (2022) 8, 10

    work page 2022

  13. [13]

    IEEE Transactions on Geoscience and Remote Sensing (2023) 2, 4, 8, 9

    Hu, Z., Gao, K., Zhang, X., Wang, J., Wang, H., Yang, Z., Li, C., Li, W.: Emo2-detr: Efficient-matching oriented object detection with transformers. IEEE Transactions on Geoscience and Remote Sensing (2023) 2, 4, 8, 9

    work page 2023

  14. [14]

    DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection

    Lang, S., Ventola, F., Kersting, K.: Dafne: A one-stage anchor-free approach for oriented object detection. arXiv preprint arXiv:2109.06148 (2021) 8

    work page internal anchor Pith review Pith/arXiv arXiv 2021

  15. [15]

    DN-DETR: Accelerate DETR Training by Introducing Query DeNoising

    Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: Dn-detr: Accelerate detr training by introducing query denoising. arXiv preprint arXiv:2203.01305 (2022) 9

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  16. [16]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Li, W., Chen, Y., Hu, K., Zhu, J.: Oriented reppoints for aerial object detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 1829–1838 (2022) 8, 10

    work page 2022

  17. [17]

    In: Proceedings of the IEEE international conference on computer vision

    Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision. pp. 2980–2988 (2017) 9, 10 14 Trong-Thuan Nguyen and Minh-Triet Tran

    work page 2017

  18. [18]

    IENet: Interacting Embranchment One Stage Anchor Free Detector for Orientation Aerial Object Detection

    Lin, Y., Feng, P., Guan, J., Wang, W., Chambers, J.: Ienet: Interacting embranch- ment one stage anchor free detector for orientation aerial object detection. arXiv preprint arXiv:1912.00969 (2019) 8

    work page internal anchor Pith review Pith/arXiv arXiv 1912

  19. [19]

    IEEE Geoscience and Remote Sensing Letters19, 1–5 (2021) 8

    Ming, Q., Miao, L., Zhou, Z., Yang, X., Dong, Y.: Optimization for arbitrary- oriented object detection via representation invariance loss. IEEE Geoscience and Remote Sensing Letters19, 1–5 (2021) 8

    work page 2021

  20. [20]

    In: Proceedings of the AAAI Conference on Artificial Intelligence

    Ming, Q., Zhou, Z., Miao, L., Zhang, H., Li, L.: Dynamic anchor learning for arbitrary-oriented object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 35, pp. 2355–2363 (2021) 8, 10

    work page 2021

  21. [21]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Pan, X., Ren, Y., Sheng, K., Dong, W., Yuan, H., Guo, X., Ma, C., Xu, C.: Dynamic refinement network for oriented and densely packed object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 11207–11216 (2020) 8

    work page 2020

  22. [22]

    Advances in neural information processing systems28(2015) 8, 9, 10

    Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems28(2015) 8, 9, 10

    work page 2015

  23. [23]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Sun, P., Zhang, R., Jiang, Y., Kong, T., Xu, C., Zhan, W., Tomizuka, M., Li, L., Yuan, Z., Wang, C., Luo, P.: Sparse r-cnn: End-to-end object detection with learnable proposals. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 14454–14463 (2021) 2

    work page 2021

  24. [24]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Xie, X., Cheng, G., Wang, J., Yao, X., Han, J.: Oriented r-cnn for object detection. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 3520–3529 (2021) 3, 4, 5, 8, 10

    work page 2021

  25. [25]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Xu, C., Ding, J., Wang, J., Yang, W., Yu, H., Yu, L., Xia, G.S.: Dynamic coarse-to- fine learning for oriented tiny object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 7318–7328 (2023) 2, 8, 9, 10

    work page 2023

  26. [26]

    IEEE transactions on pattern analysis and machine intelligence43(4), 1452–1459 (2020) 8

    Xu, Y., Fu, M., Wang, Q., Wang, Y., Chen, K., Xia, G.S., Bai, X.: Gliding vertex on the horizontal bounding box for multi-oriented object detection. IEEE transactions on pattern analysis and machine intelligence43(4), 1452–1459 (2020) 8

    work page 2020

  27. [27]

    In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VIII 16

    Yang, X., Yan, J.: Arbitrary-oriented object detection with circular smooth label. In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VIII 16. pp. 677–694. Springer (2020) 8

    work page 2020

  28. [28]

    In: Proceedings of the AAAI conference on artificial intelligence

    Yang, X., Yan, J., Feng, Z., He, T.: R3det: Refined single-stage detector with feature refinement for rotating object. In: Proceedings of the AAAI conference on artificial intelligence. vol. 35, pp. 3163–3171 (2021) 2, 4, 5

    work page 2021

  29. [29]

    In: International conference on machine learning

    Yang, X., Yan, J., Ming, Q., Wang, W., Zhang, X., Tian, Q.: Rethinking rotated object detection with gaussian wasserstein distance loss. In: International conference on machine learning. pp. 11830–11841. PMLR (2021) 8

    work page 2021

  30. [30]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Yang, X., Yang, J., Yan, J., Zhang, Y., Zhang, T., Guo, Z., Sun, X., Fu, K.: Scrdet: Towards more robust detection for small, cluttered and rotated objects. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 8232–8241 (2019) 8

    work page 2019

  31. [31]

    Advances in Neural Information Processing Systems34, 18381–18394 (2021) 8, 10

    Yang, X., Yang, X., Yang, J., Ming, Q., Wang, W., Tian, Q., Yan, J.: Learning high- precision bounding box for rotated object detection via kullback-leibler divergence. Advances in Neural Information Processing Systems34, 18381–18394 (2021) 8, 10

    work page 2021

  32. [32]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S.: Reppoints: Point set representation for object detection. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 9657–9666 (2019) 8 LOGOS: Language-guided Oriented Object Detection in Aerial Scenes 15

    work page 2019

  33. [33]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Yu, Y., Da, F.: Phase-shifting coder: Predicting accurate orientation in oriented object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 13354–13363 (2023) 8

    work page 2023

  34. [34]

    IEEE Geoscience and Remote Sensing Letters19, 1–5 (2021) 8

    Zhang, F., Wang, X., Zhou, S., Wang, Y.: Dardet: A dense anchor-free rotated object detector in aerial images. IEEE Geoscience and Remote Sensing Letters19, 1–5 (2021) 8

    work page 2021

  35. [35]

    DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection

    Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., Shum, H.Y.: Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022) 2, 6

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  36. [36]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 9759–9768 (2020) 10

    work page 2020

  37. [37]

    Deformable DETR: Deformable Transformers for End-to-End Object Detection

    Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020) 2, 3, 4, 5, 8, 9

    work page internal anchor Pith review Pith/arXiv arXiv 2010