Pith. sign in

REVIEW 2 major objections 1 cited by

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

Dynamically scaling margins by label frequency improves open-set recognition for rare pathologies in medical images.

2026-07-01 07:44 UTC pith:IBO3S53M

load-bearing objection DMDSC adds a frequency-based dynamic margin to the simplex classifier for medical OSR, but the abstract supplies no formula, ablations, or controls to show the change actually helps. the 2 major comments →

arxiv 2605.00675 v2 pith:IBO3S53M submitted 2026-05-01 cs.CV

DMDSC: A Dynamic-Margin Deep Simplex Classifier for Open-Set Recognition on Medical Image Datasets

Vishal , Arnav Aditya , Nitin Kumar , Saurabh J. Shigwan This is my paper
classification cs.CV
keywords open-set recognitionmedical image classificationclass imbalancedynamic marginsdeep simplex classifierneural collapsepathology detection
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.

Medical imaging datasets often contain far more examples of common conditions than rare ones, which creates problems for open-set recognition tasks that require both accurate classification of known classes and reliable rejection of unknowns. The paper proposes DMDSC, a modification to the deep simplex classifier that sets larger margins for classes appearing less frequently in the training labels. This adjustment applies a higher penalty to rare classes in order to produce tighter feature clusters around them. A reader would care because the method claims to work directly on naturally imbalanced data without requiring manual balancing or per-dataset tuning.

Core claim

The DMDSC framework automatically adapts class-specific margins based on label frequency, enforcing a higher penalty and tighter feature clustering for rare pathologies to counteract the effects of data imbalance, with experiments on BloodMNIST, OCTMNIST, DermaMNIST, and BreaKHis showing improved performance over prior uniform-margin simplex classifiers.

What carries the argument

The dynamic margin that increases for classes with lower label frequency inside the deep simplex classifier loss.

Load-bearing premise

Label frequency in the training set serves as a sufficient proxy for the margin size each class requires.

What would settle it

On any of the four medical test sets, the dynamic-margin model produces lower open-set metrics such as AUROC for unknown rejection than the fixed-margin baseline.

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

If this is right

  • Rare pathologies receive tighter feature clustering without harming accuracy on frequent classes.
  • The approach outperforms state-of-the-art methods across the listed medical benchmarks.
  • No dataset-specific manual tuning of margins is required.
  • The benefits of neural collapse in simplex classifiers extend to severely imbalanced settings.

Where Pith is reading between the lines

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

  • The same frequency-based margin rule could be tested on non-medical image datasets that also show long-tailed class distributions.
  • Combining the dynamic margin with uncertainty estimation modules from related work might further strengthen unknown-sample rejection.
  • Alternative proxies for margin size, such as measured feature variance per class, could be compared directly against label frequency.

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 / 0 minor

Summary. The paper proposes DMDSC, an extension of the Deep Simplex Classifier (DSC) and Uncertainty-aware DSC that incorporates a dynamic margin mechanism. Class-specific margins are automatically adapted from label frequency to impose higher penalties and tighter clustering on rare classes in imbalanced medical imaging datasets, with the goal of improving open-set recognition (OSR) performance while preserving accuracy on known classes. Experiments on BloodMNIST, OCTMNIST, DermaMNIST, and BreaKHis are reported to show outperformance over prior SOTA methods.

Significance. If the frequency-derived dynamic margins demonstrably improve OSR without dataset-specific retuning or degradation on majority classes, the work would offer a practical extension of Neural Collapse-based classifiers to the common medical-imaging imbalance setting. The approach directly targets a clinically relevant failure mode, but its significance hinges on whether the adaptation rule is shown to be robust rather than an artifact of the training distribution.

major comments (2)
  1. [Abstract] Abstract: the central claim that margins 'automatically adapt' from label frequency to enforce tighter clustering for rare pathologies is load-bearing, yet no equation, derivation, or pseudocode for the margin computation is supplied. Without this, it is impossible to determine whether the reported gains are independent of the fitting process or whether frequency is a sufficient proxy for the required separation (as questioned by the stress-test note on intra-class variance).
  2. [Abstract] Abstract (experiments paragraph): the outperformance claim is presented without reference to ablations that isolate the dynamic-margin component, without error bars, and without statistical significance tests. This leaves open whether the gains are attributable to the proposed adaptation or to other implementation choices.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. We address each major comment below and commit to revisions that strengthen the presentation of the dynamic margin mechanism and experimental claims.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim that margins 'automatically adapt' from label frequency to enforce tighter clustering for rare pathologies is load-bearing, yet no equation, derivation, or pseudocode for the margin computation is supplied. Without this, it is impossible to determine whether the reported gains are independent of the fitting process or whether frequency is a sufficient proxy for the required separation (as questioned by the stress-test note on intra-class variance).

    Authors: We agree the abstract should be self-contained on this point. The margin adaptation rule (including its dependence on label frequency) is formally defined with derivation in Section 3.2 of the full manuscript. We will revise the abstract to include the key equation and a one-sentence derivation outline so that the central claim can be evaluated without reference to the body. We will also add a brief note addressing the intra-class variance concern by explaining why frequency serves as a practical proxy in the medical imaging setting. revision: yes

  2. Referee: [Abstract] Abstract (experiments paragraph): the outperformance claim is presented without reference to ablations that isolate the dynamic-margin component, without error bars, and without statistical significance tests. This leaves open whether the gains are attributable to the proposed adaptation or to other implementation choices.

    Authors: The full manuscript already contains ablation studies (Section 4.3) that isolate the dynamic-margin component via controlled comparisons against fixed-margin DSC and UCDSC baselines. However, these are not referenced in the abstract, nor are error bars or significance tests mentioned there. We will revise the abstract to explicitly reference the ablations and will ensure the revised manuscript reports error bars across all tables plus statistical significance tests for the main OSR metrics. revision: yes

Circularity Check

0 steps flagged

No significant circularity: dynamic margin is a heuristic validated on external benchmarks

full rationale

The paper proposes DMDSC as an extension of prior DSC/UCDSC work, introducing a dynamic margin rule that sets class-specific values from label frequency counts in the training set. This is a modeling choice to address imbalance, not a derivation or prediction that reduces to the inputs by construction. Outperformance claims rest on empirical results across held-out medical datasets (BloodMNIST, OCTMNIST, DermaMNIST, BreaKHis), which are independent of the margin definition. Self-citations supply background on the simplex classifier but are not load-bearing for the new margin component. No equations, uniqueness theorems, or fitted parameters are shown to force the reported gains tautologically.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No explicit free parameters, axioms, or invented entities are identifiable from the abstract. The dynamic margin is introduced but its precise definition and any associated constants are not provided.

pith-pipeline@v0.9.1-grok · 5771 in / 917 out tokens · 32566 ms · 2026-07-01T07:44:03.415107+00:00 · methodology

0 comments
read the original abstract

Medical imaging datasets are often characterized by extreme class imbalances, where rare pathologies are significantly underrepresented compared to common conditions. This imbalance poses a dual challenge for Open-Set Recognition (OSR): models must maintain high classification accuracy on known classes while reliably rejecting unknown samples unseen during training in the clinical settings. While recently proposed Deep Simplex Classifier (DSC)~\cite{cevikalp2024reaching} and UnCertainty-aware Deep Simplex Classifier (UCDSC)~\cite{Aditya_2026_WACV} successfully leverage Neural Collapse to ensure maximal inter-class separation, they rely on a uniform margin that does not account for the varying densities of medical classes. In this paper, we propose DMDSC an enhanced framework featuring a dynamic margin approach. Our approach automatically adapts class-specific margins based on label frequency, enforcing a higher penalty and tighter feature clustering for rare pathologies to counteract the effects of data imbalance. Extensive experiments conducted on diverse medical benchmarks on BloodMNIST\cite{medmnistv2}, OCTMNIST\cite{medmnistv2}, DermaMNIST\cite{medmnistv2}, and BreaKHis~\cite{spanhol2015dataset} datasets, demonstrate that our framework outperforms state-of-the-art methods.

Figures

Figures reproduced from arXiv: 2605.00675 by Arnav Aditya, Nitin Kumar, Saurabh J. Shigwan, Vishal.

Figure 1
Figure 1. Figure 1: Illustration of the proposed open-set recognition framework with dynamic mar￾gin learning. In our proposed framework, input images are mapped to a hyperspherical embedding space where class centers (stars) are fixed at the vertices of a simplex ETF. The distance between any two class centers is d, ensuring maximal inter-class separa￾tion. Known-class samples (dots) are pulled toward their corresponding cen… view at source ↗
Figure 2
Figure 2. Figure 2: Sample images from the five datasets (a) BloodMNIST (b) OCTMNIST (c) BreaKHis (d) DermaMNIST (e) Augmented Skin Conditions 4.2 Evaluation Metrics We use accuracy (ACC) to evaluate closed-set classification performance. To measure open-set performance, we report AUROC, which is a threshold-independent [PITH_FULL_IMAGE:figures/full_fig_p010_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Ablation studies on margin parameters. Each result is the average of five runs [PITH_FULL_IMAGE:figures/full_fig_p014_3.png] 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.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Beyond the Simplex: Balanced Prototype Geometry for Scorer-Agnostic Open-Set Recognition

    cs.LG 2026-06 unverdicted novelty 7.0

    Balanced equal-norm prototype codes enable theoretical guarantees for simplex-ratio OSR in all embedding dimensions, with a dichotomy at d >= C-1 and exponential decay of false acceptance.

Reference graph

Works this paper leans on

39 extracted references · 39 canonical work pages · cited by 1 Pith paper · 2 internal anchors

  1. [1]

    Mendeley Data, V1 (2020).https://doi.org/10

    Acevedo, A., Merino, A., Alférez, S., Cabrera, J.R., Pereira, C., León, A., Sánchez, P.: A dataset for microscopic peripheral blood cell images for development of au- tomatic recognition systems. Mendeley Data, V1 (2020).https://doi.org/10. 17632/snkd93bnjr.1,https://doi.org/10.17632/snkd93bnjr.1

    work page doi:10.17632/snkd93bnjr.1 2020

  2. [2]

    Data in Brief30, 105474 (2020).https://doi.org/ 10.1016/j.dib.2020.105474

    Acevedo, A., Merino, A., Alférez, S., Cabrera, J.R., Pereira, C., León, A., Sánchez, P.: A dataset of microscopic peripheral blood cell images for development of au- tomatic recognition systems. Data in Brief30, 105474 (2020).https://doi.org/ 10.1016/j.dib.2020.105474

    work page doi:10.1016/j.dib.2020.105474 2020

  3. [3]

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

    Aditya, A., Kumar, N., Shigwan, S.: UCDSC: Open set uncertainty aware deep simplex classifier for medical image datasets. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). pp. 4787–4796 (March 2026)

    work page 2026

  4. [4]

    Bendale, A., Boult, T.E.: Towards open world recognition. CVPR pp. 1893–1902 (2015)

    work page 1902

  5. [5]

    IEEE Transactions on Neural Networks and Learning Systems36(5), 8178–8191 (2024)

    Cevikalp, H., Saribas, H., Uzun, B.: Reaching nirvana: Maximizing the margin in both euclidean and angular spaces for deep neural network classification. IEEE Transactions on Neural Networks and Learning Systems36(5), 8178–8191 (2024)

    work page 2024

  6. [6]

    Pattern Recognition138, 109385 (2023)

    Cevikalp, H., Uzun, B., Salk, Y., Saribas, H., Köpüklü, O.: From anomaly detection to open set recognition: Bridging the gap. Pattern Recognition138, 109385 (2023)

    work page 2023

  7. [7]

    IEEE Transactions on Pattern Analysis and Machine Intelligence44(11), 8065–8081 (2021)

    Chen, G., Peng, P., Wang, X., Tian, Y.: Adversarial reciprocal points learning for open set recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence44(11), 8065–8081 (2021)

    work page 2021

  8. [8]

    In: European conference on computer vision

    Chen, G., Qiao, L., Shi, Y., Peng, P., Li, J., Huang, T., Pu, S., Tian, Y.: Learning open set network with discriminative reciprocal points. In: European conference on computer vision. pp. 507–522. Springer (2020)

    work page 2020

  9. [9]

    Chin, T.J., Cai, Z., Neumann, F.: Robust fitting in computer vision: Easy or hard? In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 701–716 (2018)

    work page 2018

  10. [10]

    Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)

    Codella, N., Rotemberg, V., Tschandl, P., Celebi, M.E., Dusza, S., Gutman, D., Helba,B.,Kalloo,A.,Liopyris,K.,Marchetti,M.,etal.:Skinlesionanalysistoward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv preprint arXiv:1902.03368 (2019)

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  11. [11]

    Ad- vances in Neural Information Processing Systems31(2018)

    Dhamija, A.R., Günther, M., Boult, T.: Reducing network agnostophobia. Ad- vances in Neural Information Processing Systems31(2018)

    work page 2018

  12. [12]

    In: British Machine Vision Conference

    Ge, Z., Demyanov, S., Chen, Z., Garnavi, R.: Generative openmax for multi-class open set classification. In: British Machine Vision Conference. BMVA Press (2017)

    work page 2017

  13. [13]

    IEEE TPAMI43(10), 3614–3631 (2021)

    Geng, C., Huang, S.J., Chen, S.: Recent advances in open set recognition: A survey. IEEE TPAMI43(10), 3614–3631 (2021)

    work page 2021

  14. [14]

    IEEE transactions on pattern analysis and machine intelligence43(10), 3614–3631 (2020)

    Geng, C., Huang, S.j., Chen, S.: Recent advances in open set recognition: A survey. IEEE transactions on pattern analysis and machine intelligence43(10), 3614–3631 (2020)

    work page 2020

  15. [15]

    He,K.,Zhang,X.,Ren,S.,Sun,J.:Deepresiduallearningforimagerecognition.In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770–778 (2016)

    work page 2016

  16. [16]

    Deep Anomaly Detection with Outlier Exposure

    Hendrycks, D., Mazeika, M., Dietterich, T.: Deep anomaly detection with outlier exposure. arXiv preprint arXiv:1812.04606 (2018)

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  17. [17]

    In: Proceedings of the 7th International Conference on Learning Repre- sentations (ICLR) (2019),https://openreview.net/forum?id=HyxCxhRcY7 16 Vishal et al

    Hendrycks, D., Mazeika, M., Dietterich, T.: Deep anomaly detection with outlier exposure. In: Proceedings of the 7th International Conference on Learning Repre- sentations (ICLR) (2019),https://openreview.net/forum?id=HyxCxhRcY7 16 Vishal et al

    work page 2019

  18. [18]

    Intelligent data analysis6(5), 429–449 (2002)

    Japkowicz, N., Stephen, S.: The class imbalance problem: A systematic study. Intelligent data analysis6(5), 429–449 (2002)

    work page 2002

  19. [19]

    Cell172(5), 1122– 1131.e9 (2018).https://doi.org/10.1016/j.cell.2018.02.010

    Kermany, D.S., Goldbaum, M., Cai, W., Valentim, C.C., Liang, H., Baxter, S.L., McKeown, A., Yang, G., Wu, X., Yan, F., Dong, J., et al.: Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell172(5), 1122– 1131.e9 (2018).https://doi.org/10.1016/j.cell.2018.02.010

    work page doi:10.1016/j.cell.2018.02.010 2018

  20. [20]

    Scientific Reports15(1), 22617 (2025)

    Lin, Y., He, S., Luo, W.: Dynamic margin contrastive learning for open-set recog- nition in long-tailed sonar imagery. Scientific Reports15(1), 22617 (2025)

    work page 2025

  21. [21]

    In: International conference on medical image computing and computer-assisted intervention

    Liu, M., Xu, L., Zhang, J.: Learning large margin sparse embeddings for open set medical diagnosis. In: International conference on medical image computing and computer-assisted intervention. pp. 548–558. Springer (2023)

    work page 2023

  22. [22]

    In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision

    Miller, D., Sunderhauf, N., Milford, M., Dayoub, F.: Class anchor clustering: A loss for distance-based open set recognition. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. pp. 3570–3578 (2021)

    work page 2021

  23. [23]

    In: European conference on computer vision

    Moon, W., Park, J., Seong, H.S., Cho, C.H., Heo, J.P.: Difficulty-aware simulator for open set recognition. In: European conference on computer vision. pp. 365–381. Springer (2022)

    work page 2022

  24. [24]

    Kaggle (2023),https:// www.kaggle.com/datasets/syedalinaqvi/augmented-skin-conditions-image- dataset

    Naqvi, S.A.R.: Augmented skin conditions image dataset. Kaggle (2023),https:// www.kaggle.com/datasets/syedalinaqvi/augmented-skin-conditions-image- dataset

    work page 2023

  25. [25]

    In: ECCV

    Neal, L., et al.: Open set recognition with counterfactual images. In: ECCV. pp. 613–628 (2018)

    work page 2018

  26. [26]

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

    Oza, P., Patel, V.M.: C2ae: Class conditioned auto-encoder for open-set recogni- tion. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 2307–2316 (2019)

    work page 2019

  27. [27]

    Proceedings of the National Academy of Sciences117(40), 24652–24663 (2020)

    Papyan, V., Han, X., Donoho, D.L.: Prevalence of neural collapse during the ter- minal phase of deep learning training. Proceedings of the National Academy of Sciences117(40), 24652–24663 (2020)

    work page 2020

  28. [28]

    IEEE Transactions on Pattern Analysis and Machine Intelligence40(3), 762–768 (2018)

    Rudd, E.M., et al.: The extreme value machine. IEEE Transactions on Pattern Analysis and Machine Intelligence40(3), 762–768 (2018)

    work page 2018

  29. [29]

    IEEE TPAMI36(11), 2317–2324 (2014)

    Scheirer, W.J., Jain, L.P., Boult, T.E.: Probability models for open set recognition. IEEE TPAMI36(11), 2317–2324 (2014)

    work page 2014

  30. [30]

    IEEE transactions on pattern analysis and machine intelligence35(7), 1757–1772 (2012)

    Scheirer, W.J., de Rezende Rocha, A., Sapkota, A., Boult, T.E.: Toward open set recognition. IEEE transactions on pattern analysis and machine intelligence35(7), 1757–1772 (2012)

    work page 2012

  31. [31]

    Ieee transactions on biomedical engineering 63(7), 1455–1462 (2015)

    Spanhol, F.A., Oliveira, L.S., Petitjean, C., Heutte, L.: A dataset for breast cancer histopathological image classification. Ieee transactions on biomedical engineering 63(7), 1455–1462 (2015)

    work page 2015

  32. [32]

    IEEE transactions on pattern analysis and machine intelligence30(11), 1958–1970 (2008)

    Torralba, A., Fergus, R., Freeman, W.T.: 80 million tiny images: A large data set for nonparametric object and scene recognition. IEEE transactions on pattern analysis and machine intelligence30(11), 1958–1970 (2008)

    work page 1958

  33. [33]

    Scientific data5(1), 180161 (2018)

    Tschandl, P., Rosendahl, C., Kittler, H.: The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific data5(1), 180161 (2018)

    work page 2018

  34. [34]

    Pattern Recogni- tion126, 108564 (2022)

    Wang, Z., Dong, Q., Guo, W., Li, D., Zhang, J., Du, W.: Geometric imbalanced deep learning with feature scaling and boundary sample mining. Pattern Recogni- tion126, 108564 (2022)

    work page 2022

  35. [35]

    IEEE Access12, 122852–122877 (2024).https://doi.org/10.1109/ACCESS.2024.3442569 DMDSC 17

    Xu, Y., Wang, R., Zhao, R.W., Xiao, X., Feng, R.: Semi-supervised and class- imbalanced open set medical image recognition. IEEE Access12, 122852–122877 (2024).https://doi.org/10.1109/ACCESS.2024.3442569 DMDSC 17

    work page doi:10.1109/access.2024.3442569 2024

  36. [36]

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

    Yang, H.M., Zhang, X.Y., Yin, F., Liu, C.L.: Robust classification with convolu- tional prototype learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 3474–3482 (2018)

    work page 2018

  37. [37]

    International Journal of Computer Vision132(12), 5635–5662 (2024)

    Yang, J., Zhou, K., Li, Y., Liu, Z.: Generalized out-of-distribution detection: A survey. International Journal of Computer Vision132(12), 5635–5662 (2024)

    work page 2024

  38. [38]

    Scientific Data8(1), 1–14 (2021)

    Yang, J., Shi, Y., Ni, B., et al.: Medmnist v2: A large-scale lightweight benchmark for 2d and 3d biomedical image classification. Scientific Data8(1), 1–14 (2021)

    work page 2021

  39. [39]

    In: CVPR

    Yoshihashi, R., et al.: Classification-reconstruction learning for open-set recogni- tion. In: CVPR. pp. 4016–4025 (2019)

    work page 2019