- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 3
Read review
Paper summary
This work addresses rehearsal-free class-incremental learning by constructing and aggregating three sources of classification evidence to mitigate cross-task errors. The experimental results demonstrate the effectiveness of the proposed method.
Critical strengths
- The proposed branch-native classifier aggregation is a promising approach to mitigating cross-task errors.
- The reported performance improvements are consistent across the evaluated settings and paired experimental runs.
Critical weaknesses
- The aggregation of branch-native classifiers may introduce unequal reliability across tasks. Classes introduced in earlier tasks are supported by fewer native classifiers, which may lead to less reliable score estimates. Although the method normalizes by the number of supporting classifiers, this does not necessarily address differences in estimation reliability.
- The methodology section contains excessive implementation details, making it difficult to identify and understand the key novelty of the proposed method. A clearer presentation that emphasizes the central contribution and explains the roles of the individual components would substantially improve the paper.
- Although mitigating cross-task errors is the central motivation, the decomposition of cross-task and within-task errors is presented only in the diagnostic analysis in Figure 1. The subsequent component ablations report aggregate accuracy without showing how calibration, global-reference evidence, and branch-native evidence individually affect cross-task and within-task errors. Reporting this decomposition across components and random seeds would provide more direct evidence for the claimed mechanism.
Questions for authors
- The random-feature ridge classifier in Eq. 3 follows the approach used in RanPAC. What is the specific motivation for introducing this classifier in RIDER, and what advantages does it provide over alternative classification methods? RanPAC should also be explicitly cited when introducing the random-feature classifier.
- DUKAE and CKAA are cited as closely related methods addressing decision-level accumulation, missing-distribution handling, cross-subspace alignment, and adapter aggregation. Why are these methods not included as experimental baselines? A comparison with these methods would help clarify the advantages of RIDER over closely related approaches.
7 comments
Q1: Motivation and advantages of the random-feature ridge classifier.
We adopt this classifier from RanPAC (McDonnell et al., 2023) and will explicitly cite it when introducing Eqs. (2)–(3).
Specific motivation in RIDER. The diagonal prototype rule scores each class only in its owner branch, leaving evidence from other frozen branches unused. RIDER processes each arriving task’s training data through all available frozen branches, so branch has observed at stage . Each branch-native random-feature ridge head uses sufficient statistics accumulated from these observations and contributes scores only for supported classes, without reconstructing unobserved earlier-class statistics. To complement native heads with different class coverage, RIDER fits a separate ridge reference head in the first branch’s fixed feature space using an independent fixed random projection. Because this branch observes every task, the reference provides all-class scores in a common representation. Together, these heads supplement owner-prototype evidence using directly observed data.
Advantages over alternative classifiers. Compared with cosine prototypes, random-feature ridge uses both class-wise feature sums and the Gram matrix, incorporating second-order feature structure beyond prototypes alone. Compared with linear ridge on original features, a fixed random projection followed by ReLU provides nonlinear expressivity without learning projection parameters. Compared with iterative fitting, additive updates to the Gram matrix and feature–class sums recover the corresponding batch ridge solution over observed data for the same fixed feature map and regularization. RIDER maintains this condition by freezing each completed branch’s full shared and task-specific state while keeping its random projection and feature-extraction preprocessing fixed (Appendix C.2). Thus, statistics remain compatible across tasks, enabling classifier updates without retaining historical images or per-example features.
Our evidence ablations use identical learned branches. Removing native evidence reduces mean final accuracy by 1.52/2.13 percentage points on CIFAR-100(T=20)/ImageNet-R(T=40), while removing the global reference reduces it by 1.84/1.48 points, respectively.
Q2: Lack of experimental comparisons with closely related baselines DUKAE and CKAA.
We agree that DUKAE and CKAA are directly relevant baselines. Our original experiments cover two published task-split protocols and a range of LoRA-based and other PECL methods, but do not include direct evaluations of these two closely related approaches. DUKAE trains its all-class heads using approximated distributions for missing old-class in later subspaces, though their outputs are excluded from voting. CKAA explicitly learns to classify features projected into incorrect subspaces and uses task-confidence estimates to aggregate adapters. RIDER instead accumulates sufficient statistics of actual observations in each fixed branch and solves the corresponding ridge objective. With fixed feature maps and regularization, its accumulated-statistic solution equals batch ridge fitting on those observed features (Appendix C.2), without pseudo-feature statistics or explicit cross-subspace feature alignment. Its separately fitted global reference and calibrated owner prototypes provide complementary evidence beyond native-head voting.
We address this concern with comparisons: complete methods under matched experimental configurations in the below Table 2 (Table 2 in the revised manuscript). RIDER follows the respective DUKAE and CKAA experimental configurations and matches the comparator’s seeds 1993, 1994, and 1995. AS shown in Table 2, RIDER achieves the highest mean Final and Avg.\ accuracy. These results demonstrate that RIDER maintains strong performance across different recognition benchmarks.
Table 2: Comparison with DUKAE and CKAA on five benchmarks. Results are reported as mean ± std. over three seeds. Bold denotes the best results.
| Method | CIFAR-100 Final | CIFAR-100 Avg. | ImageNet-R Final | ImageNet-R Avg. | ImageNet-A Final | ImageNet-A Avg. | CUB-200 Final | CUB-200 Avg. | Cars-196 Final | Cars-196 Avg. |
|---|---|---|---|---|---|---|---|---|---|---|
| DUKAE | 92.39 ± 0.13 | 95.21 ± 0.07 | 81.42 ± 0.30 | 86.03 ± 0.38 | -- | -- | 89.16 ± 0.20 | 92.15 ± 0.75 | 84.59 ± 0.33 | 88.34 ± 0.54 |
| CKAA | 92.26 ± 0.39 | 95.18 ± 0.86 | 82.41 ± 0.13 | 87.20 ± 0.35 | 63.53 ± 0.66 | 71.11 ± 1.03 | -- | -- | -- | -- |
| RIDER | 92.45 ± 0.17 | 95.35 ± 0.17 | 82.50 ± 0.18 | 87.30 ± 0.05 | 64.98 ± 1.03 | 73.79 ± 1.13 | 89.89 ± 0.17 | 93.08 ± 0.58 | 84.63 ± 0.45 | 89.36 ± 0.27 |
The authors look forward to your further review
Dear Reviewer,
Thank you very much for your thoughtful review and valuable feedback.
We have carefully addressed your concerns, provided detailed responses and additional experimental results, and revised both the main manuscript and appendix accordingly. We hope these updates have adequately addressed your questions and further clarified the contributions and applicability of our method.
As the rebuttal discussion deadline is fast approaching, we would greatly appreciate it if you could review our responses and share any further feedback at your earliest convenience.
If any concerns remain or further clarification is needed, we would be more than happy to address them promptly before the discussion period concludes.
Thank you again for your time and consideration.
Best regards,
The Authors
We evaluate Full (the complete RIDER) and Full−G (RIDER removes only the global reference) after all 10 tasks, grouping test examples by the task that introduced their true class. The comparison uses identical learned branches, fitted classifiers, and normalization statistics, with only the global-reference term removed. We report three seeds on ImageNet-R and CIFAR-100 with seeds 1993, 1994, 1995.
The table reports paired accuracy gains and cross-task error reductions from adding the global reference, in percentage points. ImageNet-R and CIFAR-100 entries are mean ± sample standard deviation across seeds. Positive values indicate improvement.
The earliest, single-head classes benefit in all three ImageNet-R seeds. Their accuracy gains are +1.31/+1.47/+1.78 points, with cross-task-error reductions of 1.45/1.32/1.78 points. The combined task-1–2 group also improves in every seed: its mean accuracy rises from 83.46% to 84.37%, while cross-task error falls from 15.68% to 14.74%. CIFAR-100 provides supporting single-run evidence, with early-group accuracy increasing from 90.95% to 92.10% and cross-task error decreasing from 8.60% to 7.40%. Thus, this evidence establishes a repeatable benefit for the earliest low-support classes in, rather than a benefit confined to later classes. .
We have extended the component ablation to report cross-task and within-task errors e<sub>cross</sub> and e<sub>within</sub>, both in % alongside accuracy. Using identical learned branches, this decomposition reveals how the prediction components affect the two error types. As shown in Table 1 below (Table 4 in the revised manuscript), on CIFAR-100/ImageNet-R, calibration alone improves final accuracy over the prototype baseline by 0.56/0.45 percentage points, compared with 6.14/5.63 points for full fusion. These gains primarily arise from reduced cross-task confusion: full fusion decreases e<sub>cross</sub> from 14.10%/25.31% to 7.82%/19.69%, corresponding to reductions of 6.28/5.62 points. Meanwhile, e<sub>within</sub> changes from 0.12%/0.22% to 0.27%/0.21% and remains small across all variants. Full fusion also exceeds the best variant in both final accuracy and average accuracy. Removing calibration, native evidence, or the global reference consistently increases cross-task error and decreases both accuracy metrics. Together, these results support the complementary contributions of calibrated prototypes, branch-native evidence, and the global reference to resolving cross-task confusion.
Table 1: Evidence ablation on fixed learned RIDER branches (three seeds).* All values are reported as mean ± std. B denotes the prototype baseline; C denotes prototype calibration; N denotes branch-native ridge evidence; G denotes the global reference. B+X indicates adding only component X to the prototype baseline. Full denotes the complete RIDER framework, while Full-X denotes removing component X from RIDER.*