- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces PEEK, a plug-and-play framework that incorporates external knowledge from a frozen CLIP model to improve label disambiguation in partial label learning. The key idea is to dynamically combine CLIP-derived confidence with the predictions of the trainable model, allowing external knowledge to guide early training while gradually shifting toward the model's own predictions. To achieve this, the authors develop two weighting strategies, namely global dynamic weighting and instance-specific weighting, motivated by a theoretical analysis. Experimental results show that PEEK accelerates convergence and improves the performance of existing PLL methods.
Critical strengths
-
The paper introduces PEEK, a novel partial label learning approach that utilizes external knowledge from a pretrained CLIP model to improve label disambiguation.
-
The paper is well-organized and clearly written, making it easy to follow.
-
Extensive experiments demonstrate the effectiveness of the proposed method across various partial label learning settings.
Critical weaknesses
-
Some part of the paper needs further improvement to meet ICLR submission. In particular, several formatting issues should be addressed, such as those in Table 11.
-
The experimental results show inconsistent trends regarding the performance of ISW and GDW, with neither strategy consistently outperforming the other. Can the authors clarify under what conditions ISW is preferable to GDW, and vice versa? A more detailed analysis would help explain their respective advantages and applicability.
-
Integrate both ISW and GDW can be better than use either one? It is better to give the experimental results.
-
Since ISW already incorporates GDW through the global weighting factor, it would be valuable to investigate whether combining global decay with instance-specific weighting provides additional benefits over using either component alone. A dedicated ablation study would help clarify the contribution of each component.
-
In Table 1, several results show that higher noise rates lead to better test accuracy, which is counterintuitive. Could the authors explain why increasing label ambiguity sometimes improves classification performance?
-
Table 3 shows that the confidence component provides only marginal improvements (or even useless) at certain noise rates (e.g., and ). Could the authors explain why its contribution is limited in these settings and clarify under what conditions this component is particularly beneficial?
-
How you choose your Static weight?
-
For Table 9, the comparison can be unfair, why not use same backbone? The peak memory (15.73 GB) is not an unmanageable memory consumption.
Questions for authors
Please see the weakness.