- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
The paper investigates how fine-tuning depth (unfrozen blocks) and learning rate impact CLIP ViT-B/32 robustness to image blur. On a 20-class iNaturalist bird subset stratified by blur level, full fine-tuning with achieves 98.5% accuracy on sharp images but drops to 78.8% under slight blur, whereas partial fine-tuning remains robust. While full fine-tuning at high learning rates performs worse than partial fine-tuning on the benchmarks with synthetic degradation (Aircraft, Cars, Imagenette, and ImageNet-100), the gap between sharp and blurred images appears mainly on the Bird dataset. Tracking feature drift from the pretrained model via a fixed linear probe yields an "adaptation tolerance" metric that predicts fine-tuned classifier errors (AUC = 0.96). Finally, blur-stratified validation avoids these failure modes.
Critical strengths
Unfortunately, I cannot find a critical strength that supports acceptance. The paper is very hard to read, and several main experiments are incomplete, as described in the weaknesses. Since ICLR allows authors to revise the paper during the discussion period, I will carefully read the revised version.
Critical weaknesses
- The paper is very hard to read.
1.1 All citation uses \citet{} instead of \citep{} which makes it very hard to read.
1.2 There is a lot of jargon and rarely used terms. For example, high-dose full adaptation, dose sweep, and stratum are not used in this domain. Also, degraded data can be replaced with corrupted data (e.g., ImageNet-C). Furthermore, the authors conducted fine-tuning but refer to it as adaptation (L160), due to established fields (domain adaptation and test-time adaptation), readers will be confused.
1.3 Figures 1 and 4 are too small.
-
The paper mainly focuses on blur. It would be better if the authors moved other cases mentioned in L422-429 to the main paper instead of reporting performance with individual random seeds.
-
The authors incompletely conducted their main experiments (Table 1), and most experimental results are based on a single seed, which raises another concern about whether the paper's claims hold with other random seeds. This makes the entire paper incomplete.
-
The observation in Section 3.2 that higher learning, freezing fewer layers, makes more catastrophic forgetting (higher ) is trivial.
Questions for authors
-
In L321, what are
cosine driftandfull jump drift? -
What is in Eq. (2)?