- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes LaCoD for exemplar-free domain-incremental learning. It splits CLIP visual features into a language-aligned semantic component and a complementary residual. The residual is used for domain routing, while domain-specific prompts and classifiers handle prediction. A semantic branch is also added to reduce the effect of routing errors. Experiments on four benchmarks show improvements over existing methods.
Critical strengths
-
Strong results. LaCoD outperforms the evaluated baselines on all four benchmarks, with gains of 9.35 and 6.13 points on ImageNet-R and ImageNet-Mix.
-
Useful semantic branch. Table 4 shows that semantic projection improves accuracy on incorrectly routed samples from 61.70% to 66.12%. This supports its role in reducing the effect of routing errors.
Critical weaknesses
-
Unclear source of improvements. In Table 5, adding a linear classifier improves ImageNet-R accuracy from 66.94% to 78.46%. The residual features and semantic projection add only 0.36 and 0.52 points over their respective controls. Most of the gain comes from the classifier, while the benefit of the proposed decomposition is relatively small. The ablations also lack results across multiple seeds.
-
Missing baseline comparisons. SOYO is compared only for routing accuracy, while MoP-CLIP is missing from the main results. Both are closely related to domain routing and prediction fusion. End-to-end comparisons are needed to better assess LaCoD's contribution.
-
Storage and scalability. LaCoD stores Gaussian feature statistics and adds a prompt–classifier pair for each new domain. Although inference uses only the top two predictors, memory usage grows with the number of domains. The paper does not report the actual storage cost or how inference time changes over longer streams.
Minor typo: Sec. 4.1 refers to Appendix G for temperature sensitivity analysis, but the results are actually in Appendix F.
Questions for authors
-
Can the authors provide multi-seed ablations to better separate the gains from the linear classifier and the proposed decomposition?
-
Can the authors compare LaCoD with SOYO and MoP-CLIP on all four benchmarks using the same evaluation protocol?
-
Can the authors report the memory usage and inference time as more domains are added, including the stored Gaussian statistics?