- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes a replay-free continual-learning framework for medical multimodal class-incremental learning. It uses dimension-wise uncertainty modeling to calibrate visual feature reliability and introduces a label-guided decision module that incorporates feature-label statistics to transform aligned representations into class-discriminative decision structures. The method is evaluated on six medical class-incremental datasets and reports improvements over existing baselines, with additional analyses of feature reliability, decision geometry, robustness and component contributions.
Critical strengths
- The motivation and the structural information gap are clearly identified and convincing. The paper clearly identifies the objective mismatch between feature representation alignment method and downsream classification task, which makes aligning visual and textual representations not necessarily provide the decision structure needed to separate visually similar classes.
- The experimental analysis is thorough. The evaluation includes not only standard classification metrics but also decision-geometry measures that quantify class separation, margins, and boundary violations. These analyses are particularly informative for classification, where the quality of the learned decision boundaries is central. The geometry results provide a relatively clear picture of how uncertainty calibration and label-guided decision modeling affect both predictive performance and the underlying decision structure.
Critical weaknesses
- The novelty of the Label-Guided Decision Module relative to existing analytic continual-learning methods is unclear. The formulation of the module appears closely related to RanPAC’s decorrelated ridge-regression classifier. In particular, when the textual feature term is removed, the proposed ridge regression objective reduces to the same form, while the preceding random feature expansion also follows RanPAC. The main extension therefore appears to be incorporating aligned textual feature-label statistics into this existing analytic formulation. The paper should clarify the methodological novelty beyond adding the text branch and provide a direct experimental comparison with RanPAC under the same backbone and experimental setting.
- The experimental comparison does not sufficiently isolate where the gains come from. It is unclear whether all baselines in Table 1 use the same OpenCLIP ViT-B/16 backbone. Moreover, the current ablations do not cleanly separate the benefit of textual prompts from uncertainty calibration and label-guided decision modeling. A matched vision-only variant and experiments using a vision-only pretrained encoder, e.g., an ImageNet-pretrained ViT without a text branch, would help establish whether the gains come from the proposed components rather than the underlying multimodal representation or textual information.
Reference: Mark D. McDonnell, Dong Gong, Amin Parvaneh, Ehsan Abbasnejad, and Anton van den Hengel. RanPAC: Random Projections and Pre-Trained Models for Continual Learning. Advances in Neural Information Processing Systems (NeurIPS), 36:12022–12053, 2023.
Questions for authors
- Please clarify the implementation of the zero-shot baseline in Section 4.2.1 and Table 2. Since OpenCLIP zero-shot classification matches image features with textual class prompts, does the reported 12.92% use both image and text features? If so, the distinction between the zero-shot baseline and the visual-only NCC readout should be stated more clearly.
- Figure 3(b) needs more explanation and a clearer takeaway. Section 4.2.2 reports the evolution of one component on COVID, but it is not immediately clear what conclusion the reader should draw from it or how this observation motivates dynamic dimension-wise reliability calibration.
- Why does the full method report a Mean Last MCR of 80.27% in Table 1 but 80.31% in Table 3?
- Sections 4.3 and 4.4 could be integrated more naturally into the main experimental narrative, avoiding unnecessary fragmented paragraphs. I suggest reorganizing the experimental section around a few clear research questions, each followed by the relevant evidence and a concise takeaway, while moving some secondary tables and figures to the Appendix.