- Rating
- 3
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes Dynamic Analytical Prototypes (DAP) for few-shot class-incremental learning with a backbone adapted on the base session and frozen thereafter. It combines base-statistics-guided calibration of novel-class distributions, synthetic feature sampling, a fixed Gaussian-RBF anchor mapping, and a class-balanced ridge classifier updated recursively.
Critical strengths
-
The paper is well written and well structured.
-
The shared-feature comparisons across three datasets and three backbone families provide useful evidence that the combined classifier improves on the evaluated alternatives.
-
Incremental updates require no backbone optimization or historical raw images, and adding DAP improves both SEC-Prompt and CASP in the reported experiments.
Critical weaknesses
-
The additional contribution over prior work needs clearer discussion. PGDC appears closely related to the calibration of Goswami et al. (2024)[1]. The kernel mapping and recursive updates also build on ideas in GKEAL[2]. The class-balanced objective warrants comparison with AIR (Fang et al., 2024)[3]. Although several related methods are cited and evaluated, the methodological differences remain unclear. The ablations also do not isolate the benefit of class weighting within the same solver. These gaps make it difficult to assess the extent of the advance.
-
It is unclear whether the gains come from better retention, better learning of new classes, or both. The main comparisons report aggregate accuracy. The performance-drop metric compares different class sets and does not isolate forgetting. Table 12 examines calibration, but does not provide this comparison for the full method. Separate old- and new-class results across sessions would be helpful. Without this analysis, the claimed improvement in the stability–plasticity trade-off is difficult to assess.
[1] Dipam Goswami et al. Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers. CVPR Workshops, 2024.
[2] Huiping Zhuang et al. GKEAL: Gaussian Kernel Embedded Analytic Learning for Few-Shot Class Incremental Task. CVPR, 2023.
[3] Di Fang et al. AIR: Analytic Imbalance Rectifier for Continual Learning. arXiv:2408.10349v1, 2024.
Questions for authors
Please see Critical Weaknesses 1 and 2. In particular:
-
What is the methodological advance over [1]–[3], and what evidence isolates the benefit of class weighting?
-
How does DAP compare with the strongest baselines on old- and new-class accuracy across sessions?
7 comments
Reviewer HLy6 | Q1 (Part 2/3): Matched calibration and class-weighting controls
To quantify the statistical-construction and weighting choices discussed in Part 1, we report matched ablations below.
Table 1. Six-cell matched RBF analytical controls
Experimental protocol. CUB-200/ViT fixed cache, same RBF solver; A = real supports; B = support-only Gaussian; C = prior-calibrated Gaussian. B/C retain five supports and add 500 synthetic features per novel class. U = uniform row weights; W = inverse class-size weights
| Novel-class fitted data | U: Unweighted AVG (%) | W: Class-normalized AVG (%) |
|---|---|---|
| A · Five supports only | 82.201 ± 0.000 | 83.534 ± 0.000 |
| B · Support Gaussian +500 | 82.183 ± 0.002 | 84.300 ± 0.026 |
| C · Prior-calibrated Gaussian +500 | 85.006 ± 0.056 | 85.895 ± 0.012 |
Result interpretation. Under an equal 500-feature synthesis budget and the same class-normalized solver, C-W achieves 85.895% AVG and B-W 84.300%, a +1.595 pp difference attributable to their statistical input. Holding the calibrated rows fixed and changing only the weighting rule, C-W exceeds C-U (85.006%) by +0.889 pp. These comparisons do not make either calibration or class weighting a new algebraic invention; instead, they show why both are useful in the proposed class-expansion setting. PGDC supplies informative moments, while the class-normalized solver determines how those moments influence the shared all-class decision operator.
Table 2. Synthetic-feature count at matched budget
| Synthetic / class | B-W AVG (%) | C-W AVG (%) | C-W − B-W (pp) |
|---|---|---|---|
| 0 | 83.534 ± 0.000 | 83.534 ± 0.000 | 0.000 |
| 50 | 84.223 ± 0.047 | 85.521 ± 0.059 | +1.298 |
| 100 | 84.258 ± 0.079 | 85.706 ± 0.044 | +1.448 |
| 200 | 84.289 ± 0.029 | 85.810 ± 0.039 | +1.521 |
| 500 | 84.300 ± 0.026 | 85.895 ± 0.012 | +1.595 |
Result interpretation. The same conclusion holds when the amount of synthetic data changes. Both methods begin at 83.534% with no synthetic samples, yet C-W leads B-W by +1.298 to +1.595 pp across equal budgets of 50–500 draws per class. Since both receive the same number of rows, the advantage is linked to the calibrated distribution rather than the sheer volume of augmentation. This helps explain why the statistical construction in DAP matters before the global decision update: the shared solver can only coordinate the evidence it receives.
Table 3. Prior mean and covariance transfer
| Same-budget variant | AVG (%) |
|---|---|
| B-W · No base prior | 84.300 ± 0.026 |
| Mean transfer only | 84.618 ± 0.026 |
| Covariance transfer only | 84.576 ± 0.017 |
| C-W · Full calibrated transfer | 85.895 ± 0.012 |
Result interpretation. The moment-transfer study shows what that evidence contains. Mean-only and covariance-only transfer reach 84.618% and 84.576%, respectively, compared with 84.300% without base priors; joint transfer raises AVG to 85.895%. Both the class center and its dispersion therefore contribute. In the analytical solution, these statistics play complementary roles: the mean supplies class-specific evidence, while second moments enter the operator shared by historical and novel decisions. This is how distribution calibration contributes to DAP's global prototype formulation, rather than remaining a standalone correction to a class center.
Reviewer HLy6 | Q1 (Part 3/3): Cross-benchmark calibration evidence
The original multi-benchmark ablation complements these matched CUB-200 controls by testing PGDC within the full analytical pipeline.
Table 4. Original Table 3: calibration added to KM + GKAS
Experimental protocol. The source manuscript's ViT-B-IN21K ablation on CIFAR-100, CUB-200 and ImageNet-R; AVG is mean session-wise overall accuracy
| Benchmark | KM + GKAS AVG (%) | PGDC + KM + GKAS AVG (%) | Gain |
|---|---|---|---|
| CIFAR-100 | 89.61 | 90.61 | +1.00 |
| CUB-200 | 85.53 | 85.89 | +0.36 |
| ImageNet-R | 80.08 | 80.75 | +0.67 |
Result interpretation. The original multi-benchmark results provide a broader check. Adding PGDC to KM+GKAS increases AVG by +1.00 pp on CIFAR-100, +0.36 pp on CUB-200, and +0.67 pp on ImageNet-R. These are incremental gains on top of an already effective analytical head, so their size should be read in that context. Together with the matched controls, they show that calibrated statistics provide a repeatable contribution across benchmarks and that the contribution can be isolated under a common representation. The resulting evidence supports the role of statistical calibration within DAP's global decision coordination.
Conclusion. Relative to the cited analytical and calibration methods, DAP combines retained historical and calibrated novel-class statistics in a fixed-anchor, class-normalized objective to re-coordinate all decision prototypes. The matched and multi-benchmark comparisons support the value of its calibration and weighting choices.
Reviewer HLy6 | Q1 (Part 1/3): Comparison with prior methods and system mechanism
We greatly appreciate your expert feedback and your insightful concerns. Your concerns and questions are responded as follows:
Concern: The reviewer requests a clearer account of the methodological advance beyond prior statistical calibration, kernel recursion, and analytic class balancing, as well as a matched experiment that isolates the benefit of class weighting.
Response: We propose globally coordinated dynamic analytical prototypes (DAP) to address a central difficulty of few-shot class-incremental learning: as new classes appear, the competition among all observed categories changes, so their decision representations need to be coordinated again. DAP achieves this by placing retained historical class statistics and prior-calibrated novel-class statistics in a shared, class-normalized analytical objective. Consequently, each decision prototype wc(t)=At−1μcΨ is shaped by the accumulated second-order evidence of all observed classes, and the shared operator is updated when the label set expands—without revisiting historical images. We distinguish this design from the works named by the reviewer and then measure the respective effects of calibration and weighting.
This coordination follows directly from the analytical solution. On fixed RBF features, wc(t)=At−1μcΨ with At=∑jSjΨ+λI. Here the statistical prototype μcΨ retains evidence about class c, while the common inverse operator accounts for the second moments of all observed classes. Therefore, the arrival of a new class can change historical decision directions even when their stored class statistics remain unchanged.
Comparison with the closest methods. Goswami et al.'s C-RanPAC has already combined calibrated class statistics with analytical classification. GKEAL establishes Gaussian-RBF recursive learning with augmented-feature balancing, AIR studies inverse-class-frequency weighting for analytical classifiers, and ACIL provides the recursive least-squares foundation. DAP builds on these results by using prior-calibrated novel and retained historical statistics together in a fixed base-anchor RBF space, then optimizing their decision prototypes under a class-averaged objective. In other words, the individual mathematical tools are established; the question DAP tackles is how their joint use can keep old and new decisions coordinated as class competition evolves.
Why this combination matters. PGDC determines the first- and second-order evidence available for an incoming class. Because it uses synthetic features, however, the number of fitted rows can be much larger for a novel class than for a base class—approximately 505 versus 30 in the recorded CUB setting. GKAS therefore normalizes each class's total coefficient weight instead of letting row count determine its importance. The shared At−1 then uses these class moments to update the decisions of all observed categories. The three steps address successive parts of the same problem: estimating scarce-class evidence, controlling its influence, and coordinating global decisions.
To see whether those choices are useful rather than merely conceptually connected, we use the same frozen feature cache and RBF Ridge family in the six-cell comparison (Table 1). We then vary the synthetic budget (Table 2) and transfer the mean and covariance separately (Table 3). Finally, the original multi-benchmark ablation (Table 4) checks the additional calibration effect when KM+GKAS is already present.