- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper presents SG-MoE for zero-shot cross-modal retrieval, combining dual-stream multi-granularity learning, modality-shared experts, and MLLM-assisted semantic routing. Experiments on four benchmarks show improvements over task-specific baselines.
Critical strengths
- Reasonable design. The dual-stream architecture captures both fine-grained and semantic information, while shared experts help align different modalities.
- Solid experiments. The method is tested on four benchmarks, and the ablation studies provide useful evidence for the main components.
Critical weaknesses
- Limited impact of semantic routing. Removing semantic router learning barely changes Avg mAP (0.6027 vs. 0.6024), making its actual contribution unclear.
- Modest gains from MoE. The improvement over a single expert is relatively small. Without parameter-matched comparisons, it is hard to tell whether the gains come from expert routing or simply more model capacity.
- Training-inference mismatch. The routers use semantic concept distributions during training but receive zero vectors at inference. The paper does not clearly explain how this affects performance.
Questions for authors
- Given the small performance difference, what benefits does MLLM-assisted semantic routing offer beyond interpretability?
- Could the authors provide a parameter-matched comparison with the single-expert baseline to better justify the MoE design?