- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes Bayesian Assignment Projection (BAP) for continual generalized category discovery, aiming to correct inaccurate sample assignments before class memory construction. It combines Bayesian class-size constraints derived from base-class statistics with local geometric evidence through alternating assignment projection and Gaussian estimation. Experiments on four benchmarks demonstrate improved recognition performance, achieving an average gain of 2.68 percentage points over VB-CGCD across multiple initializations.
Critical strengths
- The paper addresses error accumulation in C-GCD by explicitly revising sample assignments before memory construction. The integration of Bayesian cardinality constraints with geometric evidence is well-motivated and supported by theoretical analysis.
- BAP improves overall recognition accuracy across four standard C-GCD benchmarks under controlled comparisons. The ablation studies further demonstrate the benefits of cardinality constraints and alternating assignment refinement, supporting the effectiveness of the proposed approach.
Critical weaknesses
- BAP relies on comparable observation scales and shared class-count statistics between base and novel classes. These assumptions may not hold in realistic long-tailed or imbalanced scenarios, potentially limiting its generalizability. The performance degradation under class-dependent subsampling further highlights this concern.
- The proposed framework assumes that the number of new classes is known at each incremental stage. This restricts its applicability to realistic open-world scenarios where novel categories emerge without prior knowledge, weakening its practical significance.
Questions for authors
- Clarify how BAP handles violations of the shared class-count assumption, particularly under long-tailed distributions or class-dependent sampling. Explain the observed performance degradation on CUB and its implications for robustness.
- Clarify how strongly BAP depends on knowing the exact number of novel classes at each stage and whether inaccurate estimates would significantly affect assignment refinement and memory construction.
Thank you for the additional experiments. However, my central concern remains unresolved. Using historical counts to constrain future novel-class counts introduces an additional structural prior not guaranteed by C-GCD; benchmark-specific count regularities should not be treated as intrinsic task properties. Furthermore, performance gains under prior mismatch do not validate this assumption. If incorrect hard constraints exclude the true assignments, improved accuracy alone does not resolve the potential inconsistency between the method’s statistical justification and its assignment behavior.