W1. The proposed mechanism is inconsistent with the stated motivation, and its magnitude is too small to explain the reported performance gains. The main text describes the method as reducing the influence of over-performing classes, but Eq. 6 adds the non-negative terms Pc and Fc to the weight, so Fc in fact amplifies the gradients of classes with higher accuracy. In terms of magnitude, wc ranges from approximately 0.55 to 5.5 at α=0.1, whereas Fc≤0.01 and Pc changes by only ±0.001 per batch. Moreover, with a batch size of 64, CIFAR-100 has fewer than one sample per class in each batch on average, so Pc is effectively a noise-driven random walk. It is therefore hard to accept that such marginal changes in weight alone raise the accuracy of MobileNetV2 on CIFAR-100 from 44.58 to 60.82, an improvement of nearly 16 points. In addition, POG+PCGrad improves F1 by only 0.01 points over Folk-only, while increasing the per-epoch training time on CIFAR-100 by roughly 19 times, so the practical benefit of the second contribution is unclear.
W2. The reliability of the results as a whole is questionable.
Since the imbalance is applied only to the training split, the test sets of CIFAR and Fashion-MNIST are balanced, in which case overall accuracy and macro recall should be identical. However, the two differ substantially in several cases, such as CIFAR-100 SCCE with Xception (Acc 64.31, Rec 48.91). In addition, macro F1 cannot exceed (macro P+macro R)/2, yet there are multiple violations of this bound; for instance, Focal+Folk with DenseNet201 on Caltech-101 reports P 87.93 and R 87.95 but F1 97.89. The numbers for the same setting also differ across tables. In particular, the MobileNetV2 CIFAR-100 SCCE baseline accuracy is 44.58 in Tables 1, 3, and 6 but 61.29 in Table 8, which means that, based on Table 8, the improvement of the proposed method is only 0.4 points. All results are from a single seed, and in the only fairness table (Table 2), the class-wise F1 standard deviation actually worsens from 5.79 to 6.16, which fails to support the "fair learning" claim in the title.
Furthermore, the positioning relative to prior work and the baseline comparisons are insufficient, making it difficult to assess the significance of the contribution. The paper claims that no existing method adapts to class-wise performance during training, but it does not discuss prior work that should be directly compared, such as CDB loss [R1], which updates weights based on class-wise accuracy, and Group DRO [R2], which increases weights according to worst-group performance. MGDA [R3] and PCGrad [R4], the original sources of POG and PCGrad, are also missing from the references. The compared methods are limited to LDAM and CB, while standard long-tail baselines such as LDAM-DRW, logit adjustment, Balanced Softmax, and decoupling (cRT) are omitted. Moreover, the paper relies solely on a non-standard protocol (75×75 resolution, a 7:1:2 split, and step imbalance), so its results cannot be compared with those reported on CIFAR-LT or ImageNet-LT. A fair comparison under the standard protocols commonly used by the above methods is necessary. The literature comparison in Table 10 lists methods unrelated to imbalance, such as Shadow loss, quantization, and edge enhancement, evaluated under different protocols, so it can hardly serve as supporting evidence. Finally, the provided link contains no code, so reproducibility is not ensured.
[R1] Sinha et al., Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance, ACCV 2020
[R2] Sagawa et al., Distributionally Robust Neural Networks, ICLR 2020
[R3] Sener & Koltun, Multi-Task Learning as Multi-Objective Optimization, NeurIPS 2018
[R4] Yu et al., Gradient Surgery for Multi-Task Learning, NeurIPS 2020