Pith. sign in

REVIEW 3 major objections 2 minor 43 references

Reviewed by Pith at T0; open to challenge.

T0 means a machine referee read the full paper against a public rubric. The mark states how deep the mechanical check went, never who wrote it. the ladder, T0–T4 →

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

T0 review · grok-4.3

Enlarging logit gaps and applying scale-aware annular penalties improves infrared small target detection without added inference cost.

2026-07-03 00:51 UTC pith:VXDMDCZ4

load-bearing objection The paper adds a logit-domain margin and annular shape penalties to an IR small target detection loss, but the abstract gives no numbers so the size of any gains is unclear. the 3 major comments →

arxiv 2607.01555 v1 pith:VXDMDCZ4 submitted 2026-07-02 cs.CV

Boosting Infrared Small Target Detection via Logit-Domain Contrast and Adaptive Shape Refinement

Handong Zeng , Zhengeng Yang , Shuai Zhang , Shikai Chen , Hongshan Yu This is my paper
classification cs.CV
keywords infrared small target detectionlogit domain marginadaptive boundary suppressionplug-and-play lossshape refinementfalse alarm focal lossIRSTD
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.

Infrared small target detection faces saturation when weak targets and clutter produce similar post-activation probabilities, plus halo artifacts from missing contour rules. The paper introduces AC-SLSIoU, a loss that first widens response gaps directly in logit space between targets and hard negatives. It then applies adaptive annular penalties around predicted boundaries, scaled to target size, to sharpen edges and suppress overflow. A focal term further down-weights persistent high-confidence false alarms. The loss attaches to any existing detector and raises both detection accuracy and shape metrics on benchmarks.

Core claim

The Adaptive-Contrastive SLSIoU loss improves detection by replacing post-activation supervision with a logit-domain margin constraint that enlarges target-to-negative gaps before softmax, combined with scale-aware annular boundary penalties that penalize halo-like overflow and enforce contour fidelity, plus focal re-weighting of high-probability negatives; these terms integrate into existing networks and raise both accuracy and shape quality with no inference overhead.

What carries the argument

AC-SLSIoU loss combining Logit-Domain Margin Constraint to separate pre-activation responses, Adaptive Boundary Suppression via scale-aware annular penalties, and False-Alarm Focal Loss.

Load-bearing premise

Core limits of earlier methods come from probability saturation after activation and absent explicit contour constraints, and that logit gap enlargement plus annular penalties will correct them without new failure modes or dataset-specific tuning.

What would settle it

Attach AC-SLSIoU to a baseline detector, train and evaluate on NUAA-SIRST or similar standard IRSTD set, and check whether precision, recall, or boundary IoU metrics show no gain or decline relative to the identical detector trained without the loss.

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

If this is right

  • Existing IRSTD detectors gain better weak-target discrimination from the logit margin term.
  • Predicted shapes become tighter and less halo-prone due to the adaptive annular penalties.
  • No extra runtime cost occurs at inference because the loss affects only training.
  • Gains appear consistently across different backbone networks in cross-evaluation.

Where Pith is reading between the lines

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

  • The logit-domain and annular-penalty ideas could transfer to other small-object detection settings that suffer probability saturation or boundary blur.
  • Training dynamics might stabilize because the margin term reduces the dominance of easy negatives early in optimization.
  • If target scales vary widely within one scene, the adaptive scaling of annular penalties may still need dataset-level adjustment to avoid under- or over-suppression.

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 / 2 minor

Summary. The paper claims that post-activation probability saturation and missing explicit contour constraints limit IRSTD performance, and introduces the plug-and-play AC-SLSIoU loss comprising Logit-Domain Margin Constraint (LDMC) to enlarge target vs. hard-negative logit gaps, Adaptive Boundary Suppression (ABS) via scale-aware annular penalties to refine contours and suppress halos, plus False-Alarm Focal Loss. It asserts seamless integration into existing detectors with no inference overhead and consistent gains in accuracy and shape quality, supported by extensive experiments and cross-backbone tests.

Significance. If the logit-domain margin enlargement and adaptive annular penalties deliver robust gains without new instabilities or per-dataset retuning, the method would offer a lightweight, generalizable improvement to IRSTD pipelines by directly targeting discrimination and boundary issues in a manner compatible with standard detector heads.

major comments (3)
  1. [§3.2] §3.2, LDMC definition: the hard-negative selection criterion and margin hyperparameter are not shown to be dataset-independent; if selection thresholds or the margin value must be retuned per dataset or backbone, this contradicts the 'seamless integration' and 'no extra tuning' claims.
  2. [§4.2] §4.2, ABS formulation: the scale-aware annulus radius estimation relies on an initial target-size prediction that may be unreliable for the smallest targets; no ablation demonstrates that this does not introduce gradient instability or halo suppression failures on sub-3-pixel targets.
  3. [Table 4] Table 4, cross-backbone rows: while mean improvements are reported, the absence of per-run variance or statistical significance tests leaves open whether the gains are consistent or could be explained by hyperparameter sensitivity in LDMC/ABS.
minor comments (2)
  1. The abstract supplies no quantitative metrics, dataset names, or backbone list; adding one representative result and the evaluation protocol would improve readability.
  2. [Eq. (8)] Notation for the annular penalty weights in Eq. (8) would benefit from an accompanying diagram showing the inner/outer radii relative to predicted target scale.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive feedback. We address each major comment below, indicating where revisions will be made to strengthen the manuscript.

read point-by-point responses

  1. Referee: [§3.2] §3.2, LDMC definition: the hard-negative selection criterion and margin hyperparameter are not shown to be dataset-independent; if selection thresholds or the margin value must be retuned per dataset or backbone, this contradicts the 'seamless integration' and 'no extra tuning' claims.

    Authors: The manuscript describes the LDMC margin and selection criterion in §3.2 but does not include explicit cross-dataset ablations confirming fixed values suffice without retuning. We will add an ablation table in the revision that applies the same fixed margin and selection rule across all reported datasets and backbones to directly support the no-extra-tuning claim. revision: yes

  2. Referee: [§4.2] §4.2, ABS formulation: the scale-aware annulus radius estimation relies on an initial target-size prediction that may be unreliable for the smallest targets; no ablation demonstrates that this does not introduce gradient instability or halo suppression failures on sub-3-pixel targets.

    Authors: The manuscript does not provide a dedicated ablation isolating sub-3-pixel targets for the ABS module. We will insert such an ablation in the revised version, reporting both detection metrics and gradient-norm statistics on the smallest targets to verify stability. revision: yes

  3. Referee: [Table 4] Table 4, cross-backbone rows: while mean improvements are reported, the absence of per-run variance or statistical significance tests leaves open whether the gains are consistent or could be explained by hyperparameter sensitivity in LDMC/ABS.

    Authors: Table 4 reports only mean values; variance and significance tests are absent. We will revise the table to include per-backbone standard deviations from repeated runs (where computational budget permits) or add a short discussion of observed run-to-run consistency. revision: partial

Circularity Check

0 steps flagged

No significant circularity in loss design or claims

full rationale

The provided abstract and description introduce LDMC, ABS, and False-Alarm Focal Loss as newly designed plug-and-play components to address identified issues like probability saturation and halo effects. No equations, derivations, or self-citations are shown that reduce these terms to fitted inputs, self-definitions, or prior author results by construction. The method is presented as independent design choices for existing detectors rather than any prediction that loops back to the same data or parameters. This matches the low circularity expectation for papers whose central contributions are explicit new constraints without load-bearing self-referential steps.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Review uses only the abstract; no explicit free parameters, background axioms, or new physical entities are named. The loss design likely contains margin and weighting hyperparameters, but none are listed or justified here.

pith-pipeline@v0.9.1-grok · 5782 in / 1029 out tokens · 37695 ms · 2026-07-03T00:51:52.739414+00:00 · methodology

0 comments
read the original abstract

Infrared small target detection (IRSTD) remains challenging due to tiny target size, low signal-to-noise ratio, severe foreground-background imbalance, and blurred boundaries in complex scenes. Existing methods usually rely on post-activation probability-domain supervision for discrimination, where weak targets and strong clutter may produce saturated and close probabilities, limiting weak-target discrimination. Meanwhile, blurred boundaries and halo-like predictions mainly stem from thermal diffusion, tiny target scale, boundary uncertainty, and insufficient explicit contour constraints. To address these issues, we propose Adaptive-Contrastive SLSIoU (AC-SLSIoU), a plug-and-play discriminative and shape-aware loss for IRSTD. Specifically, a Logit-Domain Margin Constraint (LDMC) is introduced to enlarge the response gap between targets and informative hard negatives in the logit space, thereby enhancing weak-target discrimination. Adaptive Boundary Suppression (ABS) applies scale-aware annular penalties to refine target contours and suppress halo-like overflow responses. In addition, False-Alarm Focal Loss assigns larger weights to high-probability negative samples, further penalizing persistent high-confidence false alarms. Without introducing extra inference overhead, the proposed method can be seamlessly integrated into existing detectors and consistently improves both detection accuracy and shape quality. Extensive experiments and cross-backbone evaluations demonstrate the effectiveness, robustness, and generalization ability of the proposed method for infrared small target detection.

Figures

Figures reproduced from arXiv: 2607.01555 by Handong Zeng, Hongshan Yu, Shikai Chen, Shuai Zhang, Zhengeng Yang.

Figure 1
Figure 1. Figure 1: Performance distribution of the compared methods. [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Given an infrared image, the backbone produces a logit response map supervised in both probability and logit domains. LDMC constructs target–hard [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Logit distribution comparison between target pixels and hard negative background pixels under baseline supervision and AC-SLSIoU supervision. The [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Visual comparison of different IRSTD methods. Red boxes indicate target regions and enlarged local details, blue boxes indicate missed detections, [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] 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

43 extracted references · 43 canonical work pages

  1. [1]

    Infrared small target detection with scale and location sensitivity,

    Q. Liu, R. Liu, B. Zheng, H. Wang, and Y . Fu, “Infrared small target detection with scale and location sensitivity,” inProc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2024, pp. 17490–17500

    work page 2024

  2. [2]

    SAIST: Segment any infrared small target model guided by contrastive language- image pretraining,

    M. Zhang, X. Li, F. Gao, J. Guo, X. Gao, and J. Zhang, “SAIST: Segment any infrared small target model guided by contrastive language- image pretraining,” inProc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2025, pp. 9549–9558

    work page 2025

  3. [3]

    MIRSAM: Multimodal vision-language segment anything model for infrared small target detec- tion,

    M. Zhang, Q. Xu, Y . Wang, X. Li, and H. Yuan, “MIRSAM: Multimodal vision-language segment anything model for infrared small target detec- tion,”Vis. Intell., vol. 3, no. 1, Art. no. 4, 2025

    work page 2025

  4. [4]

    Pinwheel- shaped convolution and scale-based dynamic loss for infrared small target detection,

    J. Yang, S. Liu, J. Wu, X. Su, N. Hai, and X. Huang, “Pinwheel- shaped convolution and scale-based dynamic loss for infrared small target detection,” inProc. AAAI Conf. Artif. Intell., vol. 39, no. 9, 2025, pp. 9202–9210

    work page 2025

  5. [5]

    Deep learn- ing based infrared small object segmentation: Challenges and fu- ture directions,

    Z. Yang, H. Yu, J. Zhang, Q. Tang, and A. Mian, “Deep learn- ing based infrared small object segmentation: Challenges and fu- ture directions,”Inf. Fusion, vol. 118, Art. no. 103007, 2025, doi: 10.1016/j.inffus.2025.103007

    work page doi:10.1016/j.inffus.2025.103007 2025

  6. [6]

    Optimizing intersection-over-union in deep neural networks for image segmentation,

    M. A. Rahman and Y . Wang, “Optimizing intersection-over-union in deep neural networks for image segmentation,” inProc. Int. Symp. Vis. Comput. (ISVC), 2016, pp. 234–244

    work page 2016

  7. [7]

    U-Net: Convolutional net- works for biomedical image segmentation,

    O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional net- works for biomedical image segmentation,” inProc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent. (MICCAI), 2015, pp. 234– 241

    work page 2015

  8. [8]

    Robust logit adjustment for learning with long-tailed noisy data,

    M. Chen, Y . Du, W. Jiang, B. Zhang, S. Feng, Y . Xin, and C. Wang, “Robust logit adjustment for learning with long-tailed noisy data,” in Proc. AAAI Conf. Artif. Intell., vol. 39, no. 15, 2025, pp. 15 830–15 838

    work page 2025

  9. [9]

    Entropy-driven morphological top-hat transformation for infrared small target detection,

    L. Deng, G. Xu, J. Zhang, and H. Zhu, “Entropy-driven morphological top-hat transformation for infrared small target detection,”IEEE Trans. Aerosp. Electron. Syst., vol. 58, no. 2, pp. 962–975, Apr. 2022

    work page 2022

  10. [10]

    Max-mean and max-median filters for detection of small-targets,

    S. D. Deshpande, M. H. Er, V . Ronda, and P. Chan, “Max-mean and max-median filters for detection of small-targets,” inProc. SPIE Signal Data Process. Small Targets, vol. 3809, 1999, pp. 74–83

    work page 1999

  11. [11]

    A local contrast method for small infrared target detection,

    C. L. P. Chen, H. Li, Y . Wei, T. Xia, and Y . Y . Tang, “A local contrast method for small infrared target detection,”IEEE Trans. Geosci. Remote Sens., vol. 52, no. 1, pp. 574–581, Jan. 2014

    work page 2014

  12. [12]

    Infrared small target detection based on the weighted strengthened local contrast measure,

    J. Han, S. Moradi, I. Faramarzi, H. Zhang, Q. Zhao, X. Zhang, and N. Li, “Infrared small target detection based on the weighted strengthened local contrast measure,”IEEE Geosci. Remote Sens. Lett., vol. 18, no. 9, pp. 1670–1674, Sep. 2021

    work page 2021

  13. [13]

    A local contrast method for infrared small-target detection utilizing a tri- layer window,

    J. Han, S. Moradi, I. Faramarzi, C. Liu, H. Zhang, and Q. Zhao, “A local contrast method for infrared small-target detection utilizing a tri- layer window,”IEEE Geosci. Remote Sens. Lett., vol. 17, no. 10, pp. 1822–1826, Oct. 2020

    work page 2020

  14. [14]

    Infrared patch-image model for small target detection in a single image,

    C. Gao, D. Meng, Y . Yang, Y . Wang, X. Zhou, and A. G. Hauptmann, “Infrared patch-image model for small target detection in a single image,”IEEE Trans. Image Process., vol. 22, no. 12, pp. 4996–5009, Dec. 2013

    work page 2013

  15. [15]

    Reweighted infrared patch-tensor model with both nonlocal and local priors for single-frame small target detection,

    Y . Dai and Y . Wu, “Reweighted infrared patch-tensor model with both nonlocal and local priors for single-frame small target detection,”IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 10, no. 8, pp. 3752–3767, Aug. 2017

    work page 2017

  16. [16]

    Infrared small target detection based on partial sum of the tensor nuclear norm,

    L. Zhang and Z. Peng, “Infrared small target detection based on partial sum of the tensor nuclear norm,”Remote Sens., vol. 11, no. 4, Art. no. 382, 2019

    work page 2019

  17. [17]

    Infrared dim and small target detection via multiple subspace learning and spatial-temporal patch-tensor model,

    Y . Sun, J. Yang, and W. An, “Infrared dim and small target detection via multiple subspace learning and spatial-temporal patch-tensor model,” IEEE Trans. Geosci. Remote Sens., vol. 59, no. 5, pp. 3737–3752, May 2021

    work page 2021

  18. [18]

    Asymmetric contextual modulation for infrared small target detection,

    Y . Dai, Y . Wu, F. Zhou, and K. Barnard, “Asymmetric contextual modulation for infrared small target detection,” inProc. IEEE Winter Conf. Appl. Comput. Vis. (WACV), 2021, pp. 950–959

    work page 2021

  19. [19]

    Attentional local contrast networks for infrared small target detection,

    Y . Dai, Y . Wu, F. Zhou, and K. Barnard, “Attentional local contrast networks for infrared small target detection,”IEEE Trans. Geosci. Remote Sens., vol. 59, no. 11, pp. 9813–9824, Nov. 2021

    work page 2021

  20. [20]

    Dense nested attention network for infrared small target detection,

    B. Li, C. Xiao, L. Wang, Y . Wang, Z. Lin, M. Li, W. An, and Y . Guo, “Dense nested attention network for infrared small target detection,” IEEE Trans. Image Process., vol. 32, pp. 1745–1758, 2023

    work page 2023

  21. [21]

    ISNet: Shape matters for infrared small target detection,

    M. Zhang, R. Zhang, Y . Yang, H. Bai, J. Zhang, and J. Guo, “ISNet: Shape matters for infrared small target detection,” inProc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2022, pp. 877–886

    work page 2022

  22. [22]

    RRCANet: Recurrent reusable- convolution attention network for infrared small target detection,

    Y . Liu, B. Li, T. Liu, Z. Lin, and W. An, “RRCANet: Recurrent reusable- convolution attention network for infrared small target detection,”IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 18, pp. 24632– 24646, 2025

    work page 2025

  23. [23]

    Infrared small target detection algorithm based on nested FPN and interference suppression,

    Y . Lu, C. Cheng, D. Zhao, D. Zhu, and Q. Gao, “Infrared small target detection algorithm based on nested FPN and interference suppression,” Expert Syst. Appl., vol. 274, Art. no. 127029, 2025

    work page 2025

  24. [24]

    MLP-Net: Multilayer perceptron fusion network for infrared small target detection,

    Z. Wang, C. Wang, X. Li, C. Xia, and J. Xu, “MLP-Net: Multilayer perceptron fusion network for infrared small target detection,”IEEE Trans. Geosci. Remote Sens., vol. 63, Art. no. 5601313, 2025

    work page 2025

  25. [25]

    MTMLNet: Multi-task mutual learning network for infrared small target detection and segmentation,

    B. Yang, F. Li, S. Zhao, W. Wang, J. Luo, H. Pu, M. Zhou, and Y . Pi, “MTMLNet: Multi-task mutual learning network for infrared small target detection and segmentation,”IEEE Trans. Image Process., vol. 34, pp. 4414–4425, 2025

    work page 2025

  26. [26]

    Infrared small target detection via diverse feature harmonization,

    T. Guo, B. Zhou, F. Luo, and L. Zhang, “Infrared small target detection via diverse feature harmonization,”IEEE Trans. Geosci. Remote Sens., vol. 63, pp. 1–13, 2025

    work page 2025

  27. [27]

    Multibranch mutual-guiding learning for infrared small target detection,

    Q. Li, W. Zhang, W. Lu, and Q. Wang, “Multibranch mutual-guiding learning for infrared small target detection,”IEEE Trans. Geosci. Remote Sens., vol. 63, pp. 1–10, 2025

    work page 2025

  28. [28]

    Infrared small target detection via local-global feature fusion,

    L. Wu, Y . Ma, F. Fan, and J. Huang, “Infrared small target detection via local-global feature fusion,”IEEE Signal Process. Lett., vol. 32, pp. 466–470, 2025. IEEE XXX XXX 12

    work page 2025

  29. [29]

    Triple-directional fusion attention for infrared small target detection,

    S. Wang, J. Chen, H. Chen, S. Zhu, B. Li, J. Fan, W. Li, Z. Lin, and W. An, “Triple-directional fusion attention for infrared small target detection,”IEEE Geosci. Remote Sens. Lett., vol. 22, pp. 1–5, 2025

    work page 2025

  30. [30]

    Computa- tional fluid dynamic network for infrared small target detection,

    M. Zhang, K. Yue, J. Guo, Q. Zhang, J. Zhang, and X. Gao, “Computa- tional fluid dynamic network for infrared small target detection,”IEEE Trans. Neural Netw. Learn. Syst., vol. 36, no. 8, pp. 14777–14789, Aug. 2025

    work page 2025

  31. [31]

    Infrared small target detection via structure- guided diffusion filter,

    Y . Zhang and L. Wang, “Infrared small target detection via structure- guided diffusion filter,”IEEE Trans. Geosci. Remote Sens., vol. 63, pp. 1–15, 2025

    work page 2025

  32. [32]

    FADet: A frequency- aware detection framework for infrared small target detection,

    D. Feng, J. Xu, K. Li, Z. Ma, W. Li, and D. Wang, “FADet: A frequency- aware detection framework for infrared small target detection,”IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 18, pp. 24963–24975, 2025

    work page 2025

  33. [33]

    Dynamic high-frequency convolution for infrared small target detection,

    R. Li, C. Xiao, Q. Yin, W. An, N. Chen, X. Ying, M. Li, and Y . Wang, “Dynamic high-frequency convolution for infrared small target detection,”IEEE Trans. Circuits Syst. Video Technol., early access, 2026

    work page 2026

  34. [34]

    Spatial–frequency feature learn- ing for infrared small target detection,

    Q. Li, Z. Yang, J. Cheng, and Q. Wang, “Spatial–frequency feature learn- ing for infrared small target detection,”IEEE Trans. Aerosp. Electron. Syst., vol. 62, pp. 4883–4894, 2026

    work page 2026

  35. [35]

    SAMamba: Adaptive state space modeling with hierarchical vision for infrared small target detection,

    W. Xu, S. Zheng, C. Wang, Z. Zhang, C. Ren, R. Xu, and S. Xu, “SAMamba: Adaptive state space modeling with hierarchical vision for infrared small target detection,”Inf. Fusion, vol. 124, Art. no. 103338, 2025

    work page 2025

  36. [36]

    Spectrum-assisted Mamba for infrared small target detection,

    Y . Li and L. Wang, “Spectrum-assisted Mamba for infrared small target detection,” inProc. IEEE Int. Conf. Multimedia Expo (ICME), 2025, pp. 1–6

    work page 2025

  37. [37]

    DISTA-Net: Dynamic closely-spaced infrared small target unmixing,

    S. Han, S. Yang, Y . Li, X. Zhang, X. Li, J. Yang, M.-M. Cheng, and Y . Dai, “DISTA-Net: Dynamic closely-spaced infrared small target unmixing,” inProc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2025, pp. 14655–14664

    work page 2025

  38. [38]

    DSAD: Multi-directional contrast spatial attention-driven feature distillation for infrared small target detection,

    Y . Li, B. Li, G. Zhang, J. Chen, S. Deng, and H. Zhang, “DSAD: Multi-directional contrast spatial attention-driven feature distillation for infrared small target detection,”Remote Sens., vol. 17, no. 20, Art. no. 3466, 2025

    work page 2025

  39. [39]

    Frequency-aware lightweight distillation for infrared small target detection,

    W. Cai, Y . Zhang, J. Guo, Z. Cai, X. Tu, X. Ding, C. Lin, and Y . Huang, “Frequency-aware lightweight distillation for infrared small target detection,”IEEE Trans. Aerosp. Electron. Syst., pp. 1–14, 2026

    work page 2026

  40. [40]

    Momentum contrast for unsupervised visual representation learning,

    K. He, H. Fan, Y . Wu, S. Xie, and R. Girshick, “Momentum contrast for unsupervised visual representation learning,” inProc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2020, pp. 9729–9738

    work page 2020

  41. [41]

    Weakly- supervised contrastive learning with quantity prompts for moving in- frared small target detection,

    W. Duan, L. Ji, S. Chen, S. Zhu, J. Huang, and M. Ye, “Weakly- supervised contrastive learning with quantity prompts for moving in- frared small target detection,”arXiv preprint arXiv:2507.02454, 2026

    work page arXiv 2026

  42. [42]

    Target driven adaptive loss for infrared small target detection,

    Y . Shoji, T. Toizumi, and A. Ito, “Target driven adaptive loss for infrared small target detection,” inProc. IEEE Int. Conf. Image Process. (ICIP), 2025, pp. 1139–1144

    work page 2025

  43. [43]

    HDNet: A hybrid do- main network with multiscale high-frequency information enhancement for infrared small-target detection,

    M. Xu, C. Yu, Z. Li, H. Tang, Y . Hu, and L. Nie, “HDNet: A hybrid do- main network with multiscale high-frequency information enhancement for infrared small-target detection,”IEEE Trans. Geosci. Remote Sens., vol. 63, pp. 1–15, 2025, doi: 10.1109/TGRS.2025.3574962

    work page doi:10.1109/tgrs.2025.3574962 2025