- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper introduces the Age of Learning (AoL) for continual learning with long-tailed distribution. AoL increased when a sample or class is misclasified, and AoL becomes 0 if the sample or class is correctly classified. The reset ability is different from conventional class weights or loss functions for long-tailed classificaiton. Experimental results on long-tailed CIFAR10 and CIFAR100 demonstrate that the proposed AoL slightly imporves the acccuracy compared with Softmax + class balanced.
Critical strengths
The concept of AoL is interesting. Specifically, the reset ability is new idea. The AoL can be used for sample or class weight and sampling.
Critical weaknesses
Experiments are insufficient to show the effectiveness of the proposed method. 1-1. In Table 1, the auhors select the better result between sample and class-level AoL. This is unfair. The authors must show both results.
1-2. In Table 1, the accuracy of the proposed AoL is not so improved compared with class balanced softmax.
1-3. There is no comparison with conventional methods for continual learning or long-tailed classification. The readers can not judge the effectiveness of your method without the comparison.
1-4. In Table 2, the comparison with class balanced softmax is missing.
1-5. In section 4.3, only the accuracies on Places365 and Imagenet-1K datasets are shown. The experimental deitals are missing. The auhtors used buffer capacity of 500,000. What if you change the capacity size? The sensitivity analsis of the size is required. There is no result of the case that memory buffer is not used, though the authors define the method without buffer in equation (12).
Questions for authors
Please respond to the Weakness I pointed out.
5 comments
Response to Weakness 1-2
Weakness 1-2:
In Table 1, the accuracy of the proposed AoL is not so improved compared with class balanced softmax.
Reply:
We appreciate the reviewer's observation. Our objective is not to consistently outperform Class-Balanced (CB) Loss (Cui et al., 2019) but to demonstrate that consecutive prediction-error duration provides an effective learning signal without requiring global class-frequency information.
For example, on CIFAR-10/IF-400, Softmax+AoL achieves 62.36%, compared with 61.31% for Softmax+CB and 60.32% for Softmax. Thus, AoL improves the original Softmax baseline from 60.32% to 62.36% (+2.04 points) and exceeds CB by 1.05 points. On CIFAR-100/IF-100, AoL achieves 40.51% compared with 40.40% for CB, demonstrating comparable performance.
Unlike CB, which constructs weights from class-frequency statistics, AoL determines training emphasis from persistent prediction errors. This distinction is particularly relevant in streaming learning, where the global data distribution may be unknown or evolving. Our additional experiments further evaluate AoL alongside CB under these conditions.
Manuscript revision. We have revised the discussion in Section 4.2 (page 8) as follows:
AoL's relative performance against CB varies across datasets, imbalance factors, and loss functions. The offline results show benefits over unweighted training in several settings, without establishing uniform superiority over CB. We therefore complement these comparisons with multi-seed streaming experiments and evaluations incorporating AoL into existing methods.
Manuscript revision. We have added the following interpretation to Appendix C (page 22, Interpretation of "complementary"):
Complementarity in this sense does not imply that AoL must produce an additive gain when mechanically combined with every existing rebalancing method. The offline experiments compare AoL and CB independently to isolate their respective weighting signals, whereas the online comparisons in Section 4.4 evaluate AoL in combination with seven adapted baselines, including CB, to assess its additional contribution under matched conditions.
Response to Weakness 1-3
Weakness 1-3:
There is no comparison with conventional methods for continual learning or long-tailed classification. The readers can not judge the effectiveness of your method without the comparison.
Reply:
We thank the reviewer for raising this important concern. In view of the above comments, even though conventional long-tailed methods are already represented: Table 1 explicitly compares against Class-Balanced Loss (Cui et al., 2019); we have further expanded the evaluation by conducting matched comparisons with seven online-adapted methods: CB (Cui et al., 2019), Focal Loss (Lin et al., 2017), LDAM (Cao et al., 2019), ICDW/Cyclical Weighting (Chen et al., 2025), SBS/forgetting-inspired weighting (Hacohen & Tuytelaars, 2025), EMA Error Weighting, and EMA Loss Weighting.
Each method is evaluated both independently and with AoL under identical experimental conditions on CIFAR-10 and CIFAR-100 (IF=200, Period-10, ResNet-32, K=50,000), using three random seeds (42, 1024, and 2026).
Table 3: Comparison of seven online baselines with and without AoL on CIFAR-10 and CIFAR-100 under IF=200 and Period-10. Top-1 test accuracy (%) and mean ± sample SD are reported.
| Method | Variant | CIFAR-10 (42) | CIFAR-10 (1024) | CIFAR-10 (2026) | CIFAR-10 (Mean ± SD) | CIFAR-100 (42) | CIFAR-100 (1024) | CIFAR-100 (2026) | CIFAR-100 (Mean ± SD) |
|---|---|---|---|---|---|---|---|---|---|
| CB | Baseline | 76.78 | 75.69 | 78.22 | 76.90 ± 1.27 | 46.59 | 45.73 | 45.55 | 45.96 ± 0.56 |
| CB | + AoL | 81.11 | 79.16 | 79.30 | 79.86 ± 1.09 | 46.59 | 45.73 | 45.79 | 46.04 ± 0.48 |
| Focal | Baseline | 76.70 | 74.71 | 75.50 | 75.64 ± 1.00 | 42.27 | 41.12 | 39.88 | 41.09 ± 1.20 |
| Focal | + AoL | 79.78 | 79.52 | 77.84 | 79.05 ± 1.05 | 45.43 | 45.45 | 46.01 | 45.63 ± 0.33 |
| LDAM | Baseline | 78.76 | 77.24 | 77.63 | 77.88 ± 0.79 | 42.32 | 42.44 | 44.34 | 43.03 ± 1.13 |
| LDAM | + AoL | 79.67 | 78.86 | 78.85 | 79.13 ± 0.47 | 46.94 | 45.02 | 46.56 | 46.17 ± 1.02 |
| ICDW | Baseline | 82.64 | 82.81 | 81.82 | 82.42 ± 0.53 | 52.47 | 54.12 | 53.70 | 53.43 ± 0.86 |
| ICDW | + AoL | 83.29 | 83.91 | 84.23 | 83.81 ± 0.48 | 52.47 | 54.12 | 53.70 | 53.43 ± 0.86 |
| SBS | Baseline | 76.04 | 76.53 | 76.81 | 76.46 ± 0.39 | 42.62 | 44.70 | 43.05 | 43.46 ± 1.10 |
| SBS | + AoL | 79.79 | 78.62 | 78.58 | 79.00 ± 0.69 | 44.88 | 45.14 | 45.95 | 45.32 ± 0.56 |
| EMA Error | Baseline | 78.45 | 75.82 | 78.90 | 77.72 ± 1.66 | 43.42 | 43.70 | 43.98 | 43.70 ± 0.28 |
| EMA Error | + AoL | 80.02 | 79.05 | 78.90 | 79.32 ± 0.61 | 45.97 | 44.00 | 44.57 | 44.85 ± 1.01 |
| EMA Loss | Baseline | 78.54 | 76.17 | 77.85 | 77.52 ± 1.22 | 44.11 | 43.56 | 44.02 | 43.90 ± 0.30 |
| EMA Loss | + AoL | 79.74 | 79.39 | 80.69 | 79.94 ± 0.67 | 44.85 | 45.49 | 44.96 | 45.10 ± 0.34 |
Across all three seeds, adding AoL improves 36 of the 42 comparisons and matches the remaining six, without decreasing accuracy in any comparison. These matched experiments demonstrate that AoL can complement frequency-based, difficulty-based, and historical weighting methods.
We note that these are controlled online adaptations under a fixed-label-space streaming protocol, rather than full task-incremental or class-incremental continual-learning systems.
Manuscript revision. We have added the following comparison to Section 4.4 (page 9), with results reported in Table 3 (page 10):
To assess whether AoL complements existing learning signals more comprehensively, we further implement and compare seven online-adapted baselines based on CB (Cui et al., 2019), Focal (Lin et al., 2017), LDAM (Cao et al., 2019), ICDW (Chen et al., 2025), SBS (Hacohen & Tuytelaars, 2025), EMA Error Weighting, and EMA Loss Weighting.
Each method is evaluated with and without AoL under identical conditions on CIFAR-10 and CIFAR-100, using IF-200, Period-10, ResNet-32, SGD, a buffer of K = 50,000, and three random seeds.
We have also detailed the online baseline implementations in Appendix B.2 (pages 17–19) and provided the comparison implementation in the supplementary material as "main_new.py."
Response to Weakness 1-1
Dear Reviewer vLKX,
Thank you very much for taking the time to review our submission and for providing your valuable comments and generous support. We first clarify a factual misunderstanding in the summary: AoL resets to 1, not 0, upon correct classification, as defined in Eq. (2) and illustrated in Figure 1. Below, we have carefully and fully addressed all mentioned weaknesses. The corresponding changes are highlighted in the revised PDF file for your easy reference. The additional implementation of the comparison experiments is also provided in the updated supplementary material as "main_new.py."
Regarding the concern that "experiments are insufficient to show the effectiveness of the proposed method," we have substantially expanded our experimental evaluation, including additional comparisons with existing methods, complete sample-level and class-level results, multi-seed experiments on large-scale datasets, and buffer-capacity sensitivity analyses. We address each concern below.
Weakness 1-1:
Reply:
We thank the reviewer for pointing out the potential ambiguity in Table 1. To ensure fair reporting, we have revised Table 1 to consistently report class-level AoL, rather than selecting the better result between sample-level and class-level formulations. The complete results for both formulations are provided in Appendix Table 4, with class-level results outside parentheses and sample-level results inside parentheses.
Table 1: Offline long-tail classification results on CIFAR-100 and CIFAR-10 under different IFs. Top-1 test accuracy (%). All AoL results use class-level weighting.
For example, on CIFAR-10/IF-400, class-level Softmax+AoL achieves 62.36%, compared with 60.32% for Softmax and 61.31% for Softmax+CB. The corresponding sample-level result is 63.94%, but the main table consistently reports 62.36%. Similarly, at IF-100, the main table reports the class-level result of 72.62%, rather than the higher sample-level result of 73.74%.
By consistently reporting class-level AoL in Table 1 and providing both formulations in Table 4, we eliminate the possibility of selectively reporting whichever formulation achieves higher accuracy.
Manuscript revision. We have revised Table 1 (page 8) to consistently report class-level AoL and added the following clarification to Section 4.2 (page 8):
We have also clarified the reporting convention in Appendix B.1, Table 4 (page 18):