- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies OOD detection under long-tailed distributions. The authors observe that ID class features often form multiple compact local structures beyond a single-center prototype, and propose AdaGeo: each class maintains an adaptively controlled geometric memory; geometric evidence is mixed into the classification logits with a weight during training; at inference, the energy score is fused with a geometric confidence that combines local cohesion and inter-class separation. The paper reports competitive results.
Critical strengths
- Clear motivation: the held-out multi-center distortion diagnosis directly supports the core observation that a single center is insufficient to characterize intra-class variation, and the conclusion holds consistently across the many/medium/few frequency groups.
- Training uses only ID data throughout (the auxiliary OOD set is used only for a one-time post-hoc calibration of ), and the method is 1.60–1.86× faster than PATT, which is practically appealing.
- ID classification accuracy is the best among all compared methods on all three benchmarks, with positive ACC gains over PATT.
Critical weaknesses
- The compared baselines are not comprehensive. PATT was published at AAAI 2025, and several related works have appeared over the past year, such as RSCL[1] (CVPR 2026, dynamic class-wise temperature + informative outlier mining), but none of them are compared.
- The post-hoc baselines are only MSP / Energy, etc.; the paper does not compare against recent strong post-hoc scoring baselines. The key question is: on the same geometry-trained encoder, directly applying post-hoc scoring methods — is it possible to achieve comparable or even better OOD performance without the geometric memory? In addition, BERL is cited but not included in the main comparison table.
- The paper does not run experiments on class-balanced ID data. Although this paper is mainly about LT data, I would like to see whether the geometric modeling is a general contribution. Under balanced data, the method should reduce to a "fixed multi-prototype + filtering by compactness/support" model, which can be directly compared with multi-prototype methods on standard OOD benchmarks. Moreover, under balanced data Logit Adjustment degenerates to plain CE and the "imbalance compensation" motivation of the density-aware re-weighting also disappears; only the remaining gains (if any) can then be attributed to the geometric modeling itself rather than to long-tail compensation.
- Too many hyperparameters and incomplete ablation. The paper newly introduces , , , , , , , , , , , etc. If I read the paper correctly, only , , , have sensitivity analyses, and only on the CIFAR-100-LT dataset. The overall construction is complex, but the experimental gains are limited (average AUROC on CIFAR-10-LT ties with PATT at 91.50 vs 91.50; CIFAR-100-LT +1.37; on SVHN the FPR95 of 9.84 vs PATT's 4.95 is clearly worse), which raises my concern that the gains may come from hyperparameter cherry-picking. In addition, serves three purposes (shared across sample re-weighting, geometric logits, and inference-time cohesion), enters both the training supervision and the OOD scoring through the combined logits, and the paper does not specify whether the energy score operates on the raw classification logits or the combined logits; such structural couplings cannot be attributed through one-at-a-time sweeps either.
- The OOD gains are unevenly distributed, in contrast to what the abstract suggests. Appendix B.2 shows that tail-class ACC improves (+6.04 / +8.96), yet tail-group OOD detection becomes slightly worse (AUROC −0.33/−0.12, FPR95 +1.96); the OOD gains concentrate in the well-supported many/medium groups. The paper itself admits that the tail-group OOD gap "is bounded by scarce supervision rather than by the learned geometry"; the geometric modeling therefore contributes little to the tail-group OOD scenario that needs help the most.
[1] Feng, Shuai, et al. "Long-tailed out-of-distribution detection with refined separate class learning." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2026.
Questions for authors
See Weaknesses.
5 comments
Continue ...
To W2: The main concern is twofold: (i) whether detection of comparable or better quality can be obtained on the same encoder without the geometric memory, and (ii) why BERL is not in the main table.
As for the first concern, the following two points address it:
- On the same encoder, geometric scoring is above every post‑hoc score. On CIFAR‑100‑LT we fix the trained encoder and replace only the inference score, comparing energy alone, ReAct + energy, global kNN and MSP; the kNN feature bank and the ReAct threshold are both estimated from ID training features.
| Scoring method | AUROC | AUPR‑In | AUPR‑Out | FPR95 |
|---|---|---|---|---|
| MSP | 70.47 | 72.12 | 65.85 | 71.73 |
| Global kNN | 75.66 | 76.23 | 71.48 | 65.61 |
| ReAct + energy | 75.72 | 76.62 | 69.92 | 64.60 |
| Energy only | 76.12 | 76.84 | 70.94 | 64.82 |
| AdaGeo (energy + geometry) | 76.73 | 77.66 | 71.32 | 63.47 |
We can see from the above table that, averaged over the six sets, AdaGeo is best on AUROC, AUPR‑In and FPR95. Fitting a post‑hoc score to this encoder does not improve detection, whereas the geometric term raises AUROC to 76.73 and lowers FPR95 by 1.35 points.
- Without the geometric memory the gap is larger. The first row of the ablation table (Section 5.2) is the configuration with no multi‑centre components, no density‑aware learning and no geometric score; AUROC on CIFAR‑100‑LT is 73.27, 3.46 points below the full configuration. Using geometry for training only and reverting to energy at inference gives 76.12, still 0.61 points lower. The geometric memory produces an increment at both ends: from 73.27 to 76.12 in training, 2.85 points, and from 76.12 to 76.73 in inference, 0.61 points. The former cannot be replaced by any post‑hoc score, and the latter is exactly the increment measured in the above table; the geometric memory is not an add‑on that post‑hoc scoring can stand in for.
As for the second concern, it can be addressed by the two points below.
‑ Different budget: BERL is initialized with long‑tailed self‑supervised pre‑trained weights and fine‑tuned for 20 epochs, while all methods in our main tables are trained from scratch. Directly grouping BERL alongside others within the same table would mainly reflect performance gaps stemming from backbone capacity and pre‑training corpora, rather than algorithmic improvements for long‑tailed OOD — which is the focus of our paper. Indeed, the CIFAR‑LT main tables of RSCL, PATT and EAT also exclude BERL under identical experimental conditions.
‑ Different role: Citation and a table entry serve different purposes. We cite BERL to highlight that our method is orthogonal to theirs, and thus numerical juxtaposition is unnecessary. By contrast, table entries demand results obtained under identical experimental protocols. In fact, BERL reports substantially lower in‑distribution (ID) accuracy compared with our approach and other baselines: 41.05 versus 52.05 on CIFAR‑100‑LT, an 11‑point gap. Its OOD detection metrics are produced by a model with much weaker closed‑set performance. Including BERL in the main table would mislead readers into treating it as an apples‑to‑apples baseline, despite the divergent starting conditions. For this reason, we discuss BERL via in‑text citation of its technical contribution rather than including it in the numerical table. This practice aligns with the main CIFAR‑LT tables of PATT and RSCL.
Continue ...
To W3: The main concern is whether geometric modelling constitutes a general contribution, or merely a compensatory mechanism for longtailed imbalance. We address it below.
- One concept has to be separated first, because it decides how the experiment is read: the density used in density‑aware learning is the count of components within a class, not the class frequency. In Eq. (10), the log count of each component is shifted by the largest component of the same class:
bc,k=log max(nc,k,1)−maxk'∈Kc log max(nc,k',1),
where nc,k is the cumulative assignment count of component (c,k). Balanced data equalizes Nc across classes, but nc,k stays uneven within a class, so bc,k remains non‑zero under balanced data and does not disappear with the imbalance.
- The sample weight in Eq. (9) contains no frequency either. Its numerator and denominator are both the geometric unreliability 1−ρgeo, normalised within the batch:
w(f,y)=(1−ρgeo(f,y))/(1/B Σi[1−ρgeo(fi,yi)]).
It contains no class frequency, no prior, and no Nc: a head sample and a tail sample aligned equally well with their matched components receive the same weight. The only term that does become uniform under balanced data is the prior πy in LLA, which is exactly why the balanced experiment is a clean test of the remaining parts.
- We trained AdaGeo, PATT and RSCL on balanced CIFAR‑100 and evaluated them on the same six OOD test sets:
| Method | ACC | AUROC | AUPR‑In | AUPR‑Out | FPR95 |
|---|---|---|---|---|---|
| PATT | 73.14 | 80.60 | 83.33 | 73.84 | 51.74 |
| RSCL | 72.28 | 84.41 | 85.98 | 78.96 | 47.24 |
| AdaGeo | 76.92 | 85.27 | 85.74 | 80.56 | 46.71 |
We can see from the table that on balanced datasets, AdaGeo achieves the best overall performance. It yields higher ACC and AUROC alongside lower FPR95. This further demonstrates that the ACC advantage cannot be attributed to longtailed compensation: under balanceddata settings, logit adjustment reduces to standard crossentropy and prior correction no longer takes effect. Consequently, the remaining performance gain must stem from geometric modelling itself. With these results, we believe the reviewer’s concern is largely addressed.
- To further bring out the contribution of geometric modelling, we separate the training and inference contributions: we fix one checkpoint and switch only the geometric term in the score.
| Scoring (same checkpoint) | AUROC | AUPR‑In | AUPR‑Out | FPR95 |
|---|---|---|---|---|
| Energy only | 84.31 | 85.38 | 78.65 | 48.25 |
| With the geometric term | 85.27 | 85.74 | 80.56 | 46.71 |
| Δ | +0.96 | +0.36 | +1.91 | −1.54 |
The results above show that the inferenceside performance increment does not shrink under balanceddata settings. AUROC improves and FPR95 degrades by magnitudes comparable to those observed in the longtailed setting, demonstrating that geometric scoring does not depend on prior correction. This ablation row further pinpoints the source of performance gains. With geometric scoring switched off, AUROC reaches 84.31 — nearly on par with RSCL’s 84.41 and 3.71 points above PATT’s 80.60. Therefore, the advantage over baselines under balanced data mainly stems from densityaware learning on the training side, while the inferenceside geometric term adds a further 0.96 points.
Thank the reviewer gBu6 very much for all comments.
Response to Reviewer gBu6
To W1: The main concern is whether the main tables are comprehensive. We address it below.
Our baselines are sufficiently comprehensive and reasonable. The main tables of Section 5.2 add RSCL (CVPR 2026) which we did not obtain through DBLP and Google Scholar previously. We thank the reviewer for recommending this new paper. The compared methods now cover the representative work of this line over the five years from 2022 to 2026. RSCL is evaluated on the same data split, the same six SC‑OOD test sets and the same metric implementation, so the protocol matches ours. Across the two benchmarks, AdaGeo has the best ACC and FPR95 of the three methods. On CIFAR‑100‑LT all five metrics lead: ACC is higher by a large margin of 7.88 points, and AUROC and FPR95 are better by 1.27 and 0.88 points. On CIFAR‑10‑LT ACC is higher by 8.39 points, AUROC ties with PATT at 91.50, and FPR95 is the lowest of the three. To summarize, our method is still competitive.