# ViMoE: An Empirical Study of Designing Vision Mixture-of-Experts

Source: [ViMoE: An Empirical Study of Designing Vision Mixture-of-Experts](<https://www.sota2.com/research/paper/68fa75df1e209131cea6a5a4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:43:37.123Z

Authors: Xumeng Han, Longhui Wei, Zhiyang Dou, Zipeng Wang, Chenhui Qiang, Xin He, Yingfei Sun, Zhenjun Han, Qi Tian

Published: 2024-10-21T07:51:17.000Z

## Abstract

Mixture-of-Experts (MoE) models embody the divide-and-conquer concept and are a promising approach for increasing model capacity, demonstrating excellent scalability across multiple domains. In this paper, we integrate the MoE structure into the classic Vision Transformer (ViT), naming it ViMoE, and explore the potential of applying MoE to vision through a comprehensive study on image classification and semantic segmentation. However, we observe that the performance is sensitive to the configuration of MoE layers, making it challenging to obtain optimal results without careful design. The underlying cause is that inappropriate MoE layers lead to unreliable routing and hinder experts from effectively acquiring helpful information. To address this, we introduce a shared expert to learn and capture common knowledge, serving as an effective way to construct stable ViMoE. Furthermore, we demonstrate how to analyze expert routing behavior, revealing which MoE layers are capable of specializing in handling specific information and which are not. This provides guidance for retaining the critical layers while removing redundancies, thereby advancing ViMoE to be more efficient without sacrificing accuracy. We aspire for this work to offer new insights into the design of vision MoE models and provide valuable empirical guidance for future research.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2410.15732>)

[PDF](<https://arxiv.org/pdf/2410.15732.pdf>)
