- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper is motivated by two problems of OVOD, including representation drift and spatial bias of novel regions. Two methods are proposed targeting these two problems. RKP aims to mitigate the representation drift by distilling the similarity correlations of DINOv2, and VRR tries to refine the bounding boxes generated by RPN.
Critical strengths
- This paper is well-motivated. I agree with the discussion on the representation drift and the spatial bias, which are important problems of OVOD.
- The experiments is concise and solid, including the comparison with SoTA and the ablation studies, which demonstrates the substantial improvements brought by RKP and VRR.
Critical weaknesses
- About RKP: The logical link between the representation drift and the proposal of RKP is not clear. The authors are suggested to answer my question #1.
- About VRR: To my opinion, the proposal of VRR is a heuristic post-process based on experience rather than a well-designed method. The authors are suggested to answer my question #2.
- About experiments: The comparison with SoTA faces potential unfairness due to the external model DINOv2, which requires further explanation.
Questions for authors
- About RKP: Please explain why RKP helps mitigate the representation drift. Are the vanilla RPN loss and classification loss unchanged during training? If so, would the RPN be trained to ignore novel regions and do not generate any proposal? Meanwhile, would the detection head be trained to misclassify the novel regions? These problems are likely due to the loss functions calculated on base classes, but RKP makes no modifications on existing loss functions and only adds a new one.
- About VRR: Please explain why some edges of bounding-boxes even expand after VRR (e.g., the upper boundary of the cake in Figure 5) ? Besides, Table 4 shows that VRR improves the AP50 by 1.8, but in Table 8, the gap between 40% and 100% Top-K values are only 0.3. Does VRR with a 100% Top-K value the same as the baseline? If so, why is there a gap between Table 4 and Table 8?