- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This study uses single epoch perturbations to assess temporal dynamics of human representational alignments during training stages. The authors claim that task classification accuracy can dissociate from behavioral and neural alignment, tested supervised models recover in accuracy and behavioral and neural alignment after all perturbations while CLIP VIT_B/32 does not recover in task accuracy (after early and mid perturbations), and late perturbations can transiently boost alignment.
Critical strengths
-
This study tests both neural and behavioral alignments of the model with humans under the training-phase perturbations which can help increasing our understanding of how models form human like representations in learning stages both in brain activity and perceptual judgments.
-
The category/class-level view is an interesting useful perspective to take.
Critical weaknesses
- Some experiments need important controls. Since CLIP has been perturbed for a larger percentage of the total training time than other models and the early perturbation is during the learning rate warm-up. The authors’ arguments against LR concern is not sufficient considering that the models also differ in data and schedule, other controls listed below are needed to rule these factors out.
- The alignment boost disappears after one epoch and is only present in 3 single seed runs, so the promise that the targeted interventions could steer alignment is under investigated and the proposed mechanism is only supported correlationally.
- Considering that only CLIP VIT-B/32 cannot fully recover from the early and mid perturbations, making a general claims (in abstract) could be considered overstatements that have only been addressed in the limitation section.
- Some main claims are based on results of a single seed per from-scratch model.
- No confidence intervals reported for per-run alignment results of the from-scratch models.
Questions for authors
Further experiments that could answer the questions below can address my concerns:
- How would your results change if the ImageNet models are perturbed for 3% training time (e.g. 3 epochs)?
- Would other onset perturbations (between epoch 13 to 28) in CLIP show permanent accuracy/alignment drops? This gives a better understanding of where the window closes.
- Have you considered testing your hypothesis on other models such as DINO/SimCLR to compare the results with CLIP?
- How do you explain that the CLIP VIT-B/32 results (mid-onset +0.004 to +0.013 for neural and −0.016 to +0.015 for behavioral alignment) are described as above baseline when they are comparable to baseline median epoch to epoch changes (in behavioral alignment) reported in the appendix?