- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies structured channel pruning for recognition under class imbalance, with an emphasis on preserving representations of rare classes. The proposed method, GB-DCS, models local class regions using granular balls, measures geometric changes caused by masking individual channels, and combines class balancing with a determinant criterion to retain complementary channels. Experiments on CIFAR-100-LT and ImageNet-LT show improvements over the reported pruning baselines, particularly for tail classes in several settings.
Critical strengths
- The paper addresses the meaningful problem of disproportionate accuracy loss on rare classes during model compression.
- Local geometric responses provide an intuitive basis for preserving class representations, while complementary selection accounts for channel redundancy.
- Experiments span two benchmarks and three training objectives, with substantial tail accuracy gains in some settings at matching FLOPs budgets.
- The paired ablations and geometry diagnostics provide useful evidence for the contributions of the main components.
Critical weaknesses
- Selecting configurations and checkpoints using test performance may lead to optimistic results. Validation based selection would improve reliability.
- Differences in training budgets and classifier adaptation make it difficult to isolate the benefits of the pruning criterion.
- The connection between determinant maximization and geometry preservation under joint pruning remains heuristic, with limited analysis of channel interactions.
- Selection time and memory usage are not reported, leaving the practical cost of evaluating individual channel masks unclear.
Questions for authors
Please refer to weaknesses.