- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper observes that adaptation-specific representations in CLIP base-to-novel hosts are poor standalone novel-class predictors, but still encode complementary information. It proposed REP that is a training-free inference wrapper that repurposesMMRL/MMRL++, acting as a corrective evidence rather than a predictor. Evaluated on 11 base-to-novel benchmarks across four hosts (MaPLe, PromptSRC, MMRL and MMRL++) and three seets it achieve state-of-the-art performance.
Critical strengths
-
Simple, well-motivated reframing from prediction to correction: a training-free plug-in that leaves the host and Base predictions untouched and is grounded in three diagnostics (linear probes with a shuffled-REP control, rank-locality of host errors with median ground-truth rank 3, and 15.9% frozen-CLIP recoverability of host errors) — consequential because each stage is motivated by evidence rather than asserted, and it applies to released checkpoints at 1.17–1.35× inference cost.
-
Thorough, consistent empirical protocol: 11 datasets, 4 hosts, 3 seeds with paired seed CIs excluding zero for all hosts, CD/DG transfer, component ablation, shuffled-REP control (78.30 vs 77.40), fusion and reranking controls, crossing-order and semantic-resource factorials, and an honest EuroSAT failure analysis — consequential because the gains are small (~1 pp) and this breadth makes them credible.
Critical weaknesses
-
The attribution of the gain to REP is weaker than claimed. Table 3/12 show that with standard class-name semantics REPURPOSE gives only +0.20 pp on MMRL (77.37 vs 77.17) and no gain on MMRL++ (78.30 vs 78.32 for the host), while frozen-CLIP reranking with CoPrompt descriptions alone already reaches 77.78 (MMRL). The improvement over the host therefore depends on LLM-generated CoPrompt descriptions, an external knowledge source most compared methods do not use; the fair baseline is description-based reranking/ensembling rather than the bare host — consequential because it weakens the headline narrative that repurposing REP drives the gain, and the fairness of the SOTA comparison.
-
Several design choices look tuned to the benchmark: the energy threshold (), the candidate rule, and especially the safeguard scale (fixed for all datasets, activated only on MMRL++/EuroSAT). The paper mitigates this with sensitivity analyses, but the additive complexity is a barrier to practical adoption and raises the risk that gains do not transfer to less-curated settings.
Questions for authors
-
Clarification. With class-name semantics, MMRL++ + REPURPOSE (78.30) does not exceed the host (78.32). How do you reconcile this with the claim that REP is the source of the corrective evidence, and how does REPURPOSE compare with simply giving the host the same CoPrompt descriptions (prompt ensembling or reranking)?
-
Suggestion. Were the safeguard, , and the K rule chosen without access to test results? Please report Table 1 without the safeguard, and a version where all choices are made on a held-out split of the base classes.
Thank you to the authors for the detailed responses and additional experimental results. However, my main concerns regarding limited methodological novelty and insufficient justification of the correction mechanism remain largely unresolved. While the authors clarify the motivation and provide empirical support, the proposed framework still primarily combines existing representations with standard mathematical operations. Moreover, demonstrating that semantic projection provides the best approximation within a subspace does not sufficiently explain why the resulting direction should lead to reliable corrections. The generalizability beyond prompt-based architectures also remains unclear.
Overall, I appreciate the authors' efforts during the rebuttal, but I do not find the responses sufficient to substantially change my original assessment. I therefore intend to maintain my original rating.