- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
All in one restoration is important within vision community. To advance, this paper studies the design of expert selection modules. Named as MDLE, the model uses a multiscale encoder-decoder arch and a pool of attention, CNNs, and MLPs experts, with a router combining different terms and scores to select and fuse a subset of experts. Training uses a set of losses and performance on three tasks is reported. Additional results on deblurring and low-light enhancement are also included. Ablations on factors and visual examples are provided.
Critical strengths
- Intuitive and intended routing. Clear motivations on this. A concrete architectural setting is provided for the expert pool.
- Extensive and informative ablations on the proposed method, adding credibility to this paper. Also the performance is promising.
- The paper is easy to follow. Figures, tables and formatting are good and accessible for readers.
Critical weaknesses
- Justifications are needed regarding the training datasets and baseline sources. Currently these details are not specified. Also, a point is that, the proposed model scores 34.15 dB in Tab. 1 but 34.42 dB in Tab. 3. Any different settings on this?
- The reviewer finds that, since the eye of this paper in on the interpretability, but the measurements are not that enough or thorough. While Fig. 5 shows the activation frequencies, such a difference may still from the learning, the association alone does not establish the claimed <physical decoupling> of this paper.
- Please specify or add ablations on the objective of MDL, since it uses log parameter count, but the router also adds learned scores. Consider separating the gains from these terms.
Questions for authors
See Weaknesses. The reviewer's rating of 2 is mainly based on these. When with satisfactory rebuttal, the reviewer is happy to adjust the score.