paper-with-me

Papers

Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters

2024-03-18 · CVPR 2024 1 · Jiazuo Yu, Yunzhi Zhuge, Lu Zhang, Ping Hu, Dong Wang, Huchuan Lu, You He

Continual learning can empower vision-language models to continuously acquire new knowledge, without the need for access to the entire historical dataset. However, mitigating the performance degradation in large-scale models is non-trivial due to (i) parameter shifts throughout lifelong learning and (ii) significant computational burdens associated with full-model tuning. In this work, we present a parameter-efficient continual learning framework to alleviate long-term forgetting in incremental learning with vision-language models. Our approach involves the dynamic expansion of a pre-trained CLIP model, through the integration of Mixture-of-Experts (MoE) adapters in response to new tasks. To preserve the zero-shot recognition capability of vision-language models, we further introduce a Distribution Discriminative Auto-Selector (DDAS) that automatically routes in-distribution and out-of-distribution inputs to the MoE Adapter and the original CLIP, respectively. Through extensive experiments across various settings, our proposed method consistently outperforms previous state-of-the-art approaches while concurrently reducing parameter training burdens by 60%. Our code locates at https://github.com/JiazuoYu/MoE-Adapters4CL

📄 PDF Abstract BibTeX arXiv:2403.11549

Code (2)

jiazuoyu/moe-adapters4cl 공식 구현 pytorch
aimagelab/mammoth pytorch

Tasks

Continual LearningIncremental LearningLifelong learningMixture-of-ExpertsZero-Shot Learning

Methods 이 논문이 사용한 방법론

MoE 설명 없음
Adapter 설명 없음
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning

2026-05-18 · Yang Liu, Toan Nguyen, Flora D. Salim arxiv

Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs). Although Mixture-of-Experts (MoE) architectures offer an efficient path to scalin…

Continual LearningVisual Reasoning

MoME: Mixture of Visual Language Medical Experts for Medical Imaging Segmentation

2025-10-30 · Arghavan Rezvani, Xiangyi Yan, Anthony T. Wu, Kun Han 외 arxiv

In this study, we propose MoME, a Mixture of Visual Language Medical Experts, for Medical Image Segmentation. MoME adapts the successful Mixture of Experts (MoE) paradigm, widely used in Large Language Models (LLMs), for…

Medical Image Segmentation

Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models

2025-08-01 · Hyundong Jin, Hyung Jin Chang, Eunwoo Kim arxiv

Continual learning enables pre-trained generative vision-language models (VLMs) to incorporate knowledge from new tasks without retraining data from previous ones. Recent methods update a visual projector to translate vi…

Continual Learning

Long-Tailed Distribution-Aware Router For Mixture-of-Experts in Large Vision-Language Model

2025-07-02 · Chaoxiang Cai, Longrong Yang, Minghe Weng, Xuewei Li 외 arxiv

The mixture-of-experts (MoE) architecture, which replaces dense networks with sparse ones, has attracted significant attention in large vision-language models (LVLMs) for achieving comparable performance while activating…

Lamer-SSL: Layer-aware Mixture of LoRA Experts for Continual Multilingual Expansion of Self-supervised Models without Forgetting

2026-02-13 · Jing Xu, Minglin Wu, Xueyuan Chen, Xixin Wu 외 arxiv

Despite their impressive performance, self-supervised speech models often struggle to generalize to new languages and tend to forget previously acquired knowledge during continual training. To address this, we propose La…

Language IdentificationSpeech Recognition