CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering
Xiyin Zeng, Yi Lu, Hao Wang

TL;DR
CoGR-MoE introduces a concept-guided expert routing framework for VQA that enhances expert selection stability and flexibility, leading to improved reasoning and answer accuracy.
Contribution
It leverages answer option semantics to guide expert routing and reweights experts for discriminative option representations, advancing VQA performance.
Findings
Achieves strong results across multiple VQA benchmarks.
Improves expert routing stability and flexibility.
Enhances option discrimination through reweighted representations.
Abstract
Visual Question Answering (VQA) requires models to identify the correct answer options based on both visual and textual evidence. Recent Mixture-of-Experts (MoE) methods improve option reasoning by grouping similar concepts or routing based on examples. However, unstable routing can lead to inconsistent expert selection in the same question type, while overly stable routing may reduce flexibility. To address this, we propose Concept-Guided Routing framework (CoGR-MoE), which incorporates semantics of the answer options to guide expert selection in the training phase. Next, option features are used to reweight the selected experts, producing discriminative representations for each candidate option. These option-level representations are further used for option comparison and optimized via contrastive learning. The experimental results indicate that CoGR-MoE delivers strong performance…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
