- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes VSOOD, a post-hoc out-of-distribution detector that measures how much adding a test feature increases the diversity of an in-distribution feature set as quantified by the Vendi Score. The method builds class-conditional feature statistics, uses a rank-1 approximation that retains the leading eigenvalue/eigenvector for each class, aggregates class-conditional novelty over the top-K predicted classes using probability weights, and optionally subtracts a global Vendi-based correction. Experiments on CIFAR-10, CIFAR-100, and ImageNet-1K with ResNet, ViT, and Swin architectures show competitive average performance, low inference overhead, and strong data efficiency, including results using only a small fraction of the training data.
Critical strengths
- Efficient and practical formulation. The rank-1 approximation reduces the class-conditional computation to O(CD), and the paper provides useful ablations showing that rank-1 performs very similarly to higher-rank variants on the reported ImageNet settings. The method is also attractive in low-data/access settings, where it remains effective with only a small fraction of the training data.
- Broad cross-architecture evaluation. The paper evaluates multiple post-hoc OOD paradigms on CIFAR-10/100 and ImageNet-1K using ResNet, ViT, and Swin models. VSOOD is especially competitive in the cross-architecture ImageNet average and provides a favorable accuracy/latency trade-off relative to more expensive feature-density baselines.
Critical weaknesses
-
The novelty of the Vendi-based formulation is not sufficiently isolated from a much simpler principal-direction similarity detector. Under the proposed rank-1 approximation, for a fixed class the only test-sample-dependent term in the local score is alpha_c(x) = (u_c^T h(x))^2; the remaining quantities are class constants. Thus the local VSOOD score is a monotonic transformation of squared similarity to the leading class direction. The paper does not include a direct baseline that uses this simple principal-direction score with the same top-K probability weighting (and, if desired, the same global correction). This comparison is important for establishing that the gain comes from the Vendi/diversity formulation rather than from a simple first-principal-direction score plus aggregation. This concern is reinforced by Table 4, where a probability-weighted RMDS++ hybrid is already very competitive and is better than VSOOD in some settings. The paper should therefore moderate the 'new paradigm' framing unless this contribution is more clearly isolated.
-
The empirical evidence is strong in aggregate but not consistently superior enough to fully support the broad state-of-the-art framing. On ImageNet-1K, VSOOD is clearly weaker than activation-shaping methods on ResNet-50 and is slightly below RMDS++ on ViT-B/16, while its main advantage appears in the cross-architecture average and on Swin-T. The CIFAR gains are comparatively modest. In addition, although the baseline suite contains several recent methods, it does not appear fully current for a 2027 submission (e.g., recent 2025-2026 post-hoc methods, which weakens the strongest SOTA claims. There is also some asymmetry in tuning effort: VSOOD receives a nontrivial grid search over (K, gamma, g), whereas KPCA uses recommended defaults because a full sweep is considered too expensive. Finally, the presentation could be substantially improved: Section 3 devotes too much main-text space to algebraic expansions and perturbation details. The core method would be easier to assess if the main text retained only the definition, final rank-1 score, aggregation, and algorithmic intuition, with most intermediate derivations moved to the appendix.
Questions for authors
-
Could the authors add a simple principal-direction baseline based directly on alpha_c(x) = (u_c^T h(x))^2, using exactly the same top-K probability weighting and global-correction protocol as VSOOD? If such a baseline performs substantially worse, it would materially strengthen the claim that the Vendi formulation contributes beyond first-principal-direction similarity; if it performs similarly, the novelty claim should be reconsidered.
-
Could the authors update the comparison with the most relevant recent post-hoc OOD methods (including representative 2025-2026 approaches) and provide a clearer architecture-wise analysis of where VSOOD helps or fails? In particular, why does VSOOD underperform the best activation-shaping methods on ResNet-50 but become strongest on Swin-T, and does this behavior persist under a matched hyperparameter-tuning budget across methods?
2 comments
Response to Reviewer haMH (continued)
Expanded Experimental Evaluation and Recent Baselines
To strengthen the empirical evaluation, we added four ImageNet architectures: DenseNet-201, MaxViT-T, MobileNetV3-Large, and Inception-v3. These extend our evaluation from three to seven pretrained classifiers, spanning convolutional, transformer, and hybrid architectures.
We also added five recent post-hoc OOD detection methods: LogitGAP [1], RAS [2], CADRef [3], FOLD [4], and BNP4OOD [5]. These span logit-based detection, activation shaping, feature geometry, and Bayesian nonparametric modeling. We additionally updated the KPCA implementation to the 2026 TPAMI version [6], as requested by another reviewer. The kPCA results now sweep over 64 configurations of kernel bandwidth and PCA dimension.
The expanded results are provided in revised Table 2, with architecture-specific results in Tables 7–13. Averaged across all seven ImageNet architectures, VSOOD achieves the strongest performance on Near-OOD and Far-OOD sets.
| Method | Near-OOD AUROC AVG | Far-OOD AUROC AVG |
|---|---|---|
| MSP | 75.78 | 85.31 |
| ASH | 57.69 | 62.16 |
| SCALE | 67.57 | 77.20 |
| ADASCALE | 74.74 | 90.02 |
| GEN | 77.36 | 89.60 |
| IODIN | 75.83 | 86.30 |
| KNN | 68.88 | 86.85 |
| FDBD | 72.78 | 88.86 |
| NCI | 74.25 | 90.04 |
| KPCA | 62.35 | 82.72 |
| RMDS++ | 78.50 | 90.45 |
| Fold | 74.50 | 87.08 |
| LogitGAP | 77.49 | 89.07 |
| BNP4OOD | 76.59 | 86.59 |
| RAS | 72.81 | 88.61 |
| CADRef | 74.75 | 91.51 |
| VSOOD | 80.33 | 93.04 |
Compared with the strongest competing methods, VSOOD improves average near-OOD AUROC by 1.83 points and far-OOD AUROC by 1.53 points. It also achieves the lowest average FPR@95 (41.61 versus 46.73 for the next-best method). Across the seven architectures, VSOOD achieves the highest average AUROC on four and ranks among the top three on all seven. These additional experiments show that the advantages are not confined to Swin-T or a particular family of pretrained classifiers.
Architecture-Specific Performance
We also investigated why activation-shaping methods perform particularly well on ResNet-50 but degrade on architectures such as Swin-T.
Prior work by [7] motivates activation scaling through the observation that ID samples often have larger positive activations than OOD samples. We examined this relationship across all seven ImageNet models and added the results to Table 14.
| ImageNet-1K Model | ID Mean | OOD Mean | ID/OOD Ratio |
|---|---|---|---|
| ResNet-50 | 0.4670 | 0.3797 | 1.230 |
| ViT-B/16 | 0.2217 | 0.2571 | 0.862 |
| Swin-T | 0.1814 | 0.2223 | 0.816 |
| DenseNet-201 | 0.2568 | 0.2270 | 1.131 |
| MaxViT-T | 0.1295 | 0.1496 | 0.866 |
| MobileNetV3-Large | 0.1352 | 0.1493 | 0.905 |
| Inception-v3 | 0.2515 | 0.2854 | 0.881 |
The activation-shaping methods ADASCALE and SCALE provide strong performance on ResNet (Table 8) and DenseNet (Table 10) - the two models for which the assumption in [7] is true. VSOOD outperforms ADASCALE on all other baselines. We have added this new analysis and discussion to our paper in Table 14 and Section 4.1.
Improved Presentation
We have incorporated your feedback in Section 3. We moved most intermediate derivations to the appendix, removed redundant equations, and re-phrased certain parts to improve its overall readability.
References
[1] Liang, Jiachen, et al. "Revisiting logit distributions for reliable out-of-distribution detection." Advances in Neural Information Processing Systems (2025).
[2] Guglielmo, Gianluca, and Marc Masana. "Ranked Activation Shift for Post-hoc Out-of-Distribution Detection." European Conference on Computer Vision. (2026).
[3] Ling, Zhiwei, et al. "Cadref: Robust out-of-distribution detection via class-aware decoupled relative feature leveraging." 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. (2025).
[4] Park, Seonghwan, et al. "Exploiting Local Flatness for Efficient Out-of-Distribution Detection." European Conference on Computer Vision. (2026).
[5] Linderman, Randolph W., et al. "A bayesian nonparametric perspective on mahalanobis distance for out of distribution detection." Transactions on Machine Learning Research (2026).
[6] Fang, Kun, et al. "Kernel PCA for out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation." IEEE Transactions on Pattern Analysis and Machine Intelligence (2026).
[7] Xu, Kai et. al, “Scaling for training time and post-hoc out-of-distribution detection enhancement.” arXiv:2310.00227 (2023).
Response to Reviewer haMH
We thank the reviewer for their feedback.
Contribution of VSOOD Beyond Principal-Direction Similarity
Following the reviewer's suggestion, we introduce a new baseline to isolate the contribution of the Vendi novelty formulation. We call this baseline PCA-Align for simplicity. PCA-Align replaces the class-conditional Vendi novelty with 1−αc(x), where αc(x)=(uc⊤h(x))2 measures squared alignment with the leading class eigenvector. We make the analogous substitution for the global correction: SPCA-Align(x)=∑c∈TK(x)pc(x)γ(1−αc(x))−g(1−αglobal(x))
PCA-Align retains VSOOD's top-K class selection, probability weighting, global-correction structure, and hyperparameter-selection protocol, replacing only the Vendi novelty terms with their alignment-based counterparts. Unlike incremental Vendi novelty, these alignment scores do not require normalization by training-set size. Thus, the comparison directly tests whether principal-direction alignment is sufficient to explain VSOOD's performance.
We also add Centroid-Align, which replaces the Vendi novelty terms with cosine distance to class centroids. These baselines are described in Section 4.2 and results are reported in revised Table 4 in the main text.
To address the concern about tuning fairness, we reimplemented all KPCA-based experiments, including standalone KPCA and the KPCA+GEN hybrid, using the updated TPAMI 2026 method [1] and tuning kernel bandwidth and PCA dimension for each setting. The resulting average AUROC comparisons are:
VSOOD outperforms PCA-Align, Centroid-Align, and Hybrid RMDS++ individually on 8 of 9 settings, and KPCA+GEN on all 9 settings. It achieves the highest AUROC on six settings and ranks second on the remaining three. Averaged across seven ImageNet architectures, VSOOD improves AUROC by 1.20 points over PCA-Align and 0.90 points over Centroid-Align.
Mathematical Distinction from PCA Similarity
We agree with the reviewer that, for a fixed class, the rank-1 Vendi novelty is a monotonic function of the squared principal-direction alignment. However, this does not imply that VSOOD and PCA-Align produce equivalent OOD scores, as they transform and aggregate these class-conditional similarities differently.
As shown in Appendix A.2, the leading-order form of our novelty score is NcΔc(x)≈2(1−αc(x)/λc), compared with the squared projection residual 1−αc(x) used by PCA-Align. The normalization by λc has a natural interpretation: it is the average squared alignment of the training samples with the class's leading eigenvector, Nc1∑i:yi=c(uc⊤h(xi))2=uc⊤ρcuc=λc.
Thus, VSOOD measures a sample's alignment relative to what is typical for its class. Since the eigenvalue λc varies across classes, this distinction matters when combining class-conditional novelty scores through probability-weighted aggregation.
References
[1] Fang, Kun, et al. "Kernel PCA for out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation." IEEE Transactions on Pattern Analysis and Machine Intelligence (2026).