- Rating
- 1
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes a spatial positive–unlabeled training objective for reconstruction-based anomaly detection with contaminated training data and a small set of labeled anomalies. Building on a DINOv2 reverse-distillation backbone, it uses per-image Otsu thresholding to divide reconstruction-error maps into flagged and complementary regions. An asymmetric objective combines reconstruction on unlabeled images with a positive-sample hinge loss and a complementary-region anchor. Results across 30 Real-IAD categories show encouraging detection and localization improvements, although the theoretical interpretation and experimental attribution require further clarification.
Critical strengths
- Practical problem, and the spatial objective makes sense. The paper tackles contamination in supposedly normal training data while only using image-level anomaly labels. I like the way it treats labeled anomalies and uncertain unlabeled samples differently: confirmed anomalies get separation pressure, while unlabeled ones only get reconstruction pressure. This seems like a useful design principle for bringing limited anomaly supervision into reconstruction-based detectors.
- The reported gains are quite encouraging across a fairly diverse benchmark. On 30 Real-IAD categories, Table 1 shows mean Image-AUROC going from 0.869 to 0.928 and PRO from 0.932 to 0.956 over RD. The evaluation covers both detection and localization, and Appendix B gives significance tests across categories instead of relying only on aggregate numbers.
Critical weaknesses
- The evaluation is limited to Real-IAD. Real-world industrial defects vary widely in appearance, size, and type. Although Real-IAD covers 30 categories, results on a single dataset provide limited evidence of generalization. Additional experiments on datasets such as MVTec AD and VisA under the same PU setting would strengthen the evaluation.
- The computational efficiency is not evaluated. The paper provides training settings but does not report training time, inference speed, or GPU memory usage. A comparison with RD and other baselines would help clarify the extra cost of the proposed training objective and its practicality for industrial applications.
- The benefit of Otsu thresholding is not directly verified. The paper argues that per-image adaptive thresholding is preferable to fixed top- selection, but does not compare them under the same training objective. Such a comparison would help establish whether the adaptive split contributes to the reported gains.
- The impact of contamination rate is not sufficiently explored. Handling contaminated training data is central to this work, but the paper does not systematically evaluate how performance changes as the contamination rate increases. Such experiments would help clarify the method’s robustness under different levels of contamination.
Questions for authors
Please see weaknesses.
2 comments
My opions after reading the rebuttal
Thanks for the detailed response. The newly added experiments on MVTecAD and ViSA strengthen the paper greatly. Yet, the evaluation metrics adopted are limited (I-AUC and PRO), it is recommended to incorporate more comprehensive metrics, such mAD [1] to see its effectiveness comprehensively. Minor issues: Inconsistent symbols for metrics, such as AUC-I and I-AUC. Besides, this method depends on Dinomaly. However, the reviewer thinks it should not be treated as a baseline, as it is trained without any correction. It should design an experiment by adding some naive baseline upon Dinomaly tailored to this setting. Moreover, Dinomaly, which is misdescribed as "RD is Dinomaly (Guo et al., 2025), a reverse distillation architecture" by the authors. In fact, it is a reconstruction-based method. Given all these points, the reviewer keep the rating. [1] Zhang, Jiangning, et al. "Exploring plain vit reconstruction for multi-class unsupervised anomaly detection." arXiv preprint arXiv:2312.07495 (2023).
We thank the reviewer for the useful comments. In the following, we address the questions and the weaknesses.
Evaluation beyond Real-IAD (added to the Supplementary Material, Section "Additional quantitative results"). We added results on VisA and MVTec AD under the same PU setting (Tables 6 and 7), where our method also outperforms or is comparable to the selected baselines.
Computational cost (added to the Supplementary Material, Section "Computational cost"). We report training time, inference cost and GPU memory for all methods, measured on a single H200 GPU (VisA; 50 epochs and batch 16 for gradient-trained methods). Inference: our method uses the Dinomaly architecture, so its inference cost is identical to RD (229.6 GFLOPs, 29 ms/image). Training: the only extra cost is passing one labeled mini-batch P through the student alongside U (the Otsu split is negligible), which gives ≈1.3× RD's training time (17.2 vs. 13.4 min on cashew, 30.0 vs. 22.8 min on candle) and 19.3 vs. 13.4 GB peak memory. LOE, SOEL and PUAE are adapted to the same architecture, so they share its inference cost. SOEL and PUAE also use P in their loss and match our training cost, while LOE matches RD. MeDS is about 8$\times$ more expensive to train (135 min over three stages). SoftPatch builds its memory bank quickly but is about 5$\times$ slower at inference (148 ms/image) due to nearest-neighbour search. In industrial use, a model is trained once and then inspects every product on the line, so a one-time training overhead with unchanged inference cost is practical.
Otsu split vs. fixed top-k (added to the Supplementary Material, Section "Additional ablations"). We constructed an ablation Otsu split vs. a fixed top-k selection, e.g., for k=5%. We trained this ablation under the same objective on VisA dataset. Image-AUROC is comparable between the two, but PRO (localization) consistently favors the Otsu split. We attribute this to defect size varying across images.
Additionally, we performed the following diagnostics. We visualize the dynamics of the inside/outside separation on the hidden GT defect mask over training on the unlabeled dataset Utrain (Fig. 7). Early in training, the fixed top-5% split's separation is briefly higher than Otsu's (the model is still training and not yet converged). It then degrades monotonically for the rest of training, ending lower than Otsu's. Real defects occupy a different, and unknown in advance, fraction of the image than the fixed size. Therefore, the fixed split can end up pushing down (anchoring) genuine defect pixels, or pushing up (hinging) genuine background pixels, instead of the correct ones. In contrast, Otsu's separation does not degrade as much as the top-5%.
Impact of the contamination rate (added to the main text, Section "Ablation study"). We sweep the contamination rate α of the unlabeled pool while keeping the labeled pool and the test split fixed, on both Real-IAD and VisA (Fig. 4). The gap between our method and RD grows monotonically with the contamination rate, for both Image-AUROC and PRO. Please see our response to Reviewer z6cF (point "Sensitivity analysis", a) for the full setting and discussion.