Meta-Adapter: An Online Few-shot Learner for Vision-Language Model

2023/11/07 by Cheng Cheng, Lin Song, Cheng, Cheng +11 · 15 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications

paper · pdf · doi:10.48550/arxiv.2311.03774

openalex publication_date 2023/11/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The contrastive vision-language pre-training, known as CLIP, demonstrates remarkable potential in perceiving open-world visual concepts, enabling effective zero-shot image recognition. Nevertheless, few-shot learning methods based on CLIP typically require offline fine-tuning of the parameters on few-shot samples, resulting in longer inference time and the risk of over-fitting in certain domains. To tackle these challenges, we propose the Meta-Adapter, a lightweight residual-style adapter, to refine the CLIP features guided by the few-shot samples in an online manner. With a few training samples, our method can enable effective few-shot learning capabilities and generalize to unseen data or tasks without additional fine-tuning, achieving competitive performance and high efficiency. Without bells and whistles, our approach outperforms the state-of-the-art online few-shot learning method by an average of 3.6% on eight image classification datasets with higher inference speed. Furthermore, our model is simple and flexible, serving as a plug-and-play module directly applicable to downstream tasks. Without further fine-tuning, Meta-Adapter obtains notable performance improvements in open-vocabulary object detection and segmentation tasks.

Cited by

• Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors
• ΔEnergy: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
• Self Identity Mapping
• Attn-Adapter: Attention Is All You Need for Online Few-shot Learner of Vision-Language Model
• Robust Prompt Tuning for Vision-Language Models with Mild Semantic Noise
• Color as the Impetus: Transforming Few-Shot Learner
• MSGCoOp: Multiple Semantic-Guided Context Optimization for Few-Shot Learning
• Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration
• Enabling Validation for Robust Few-Shot Recognition
• SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation
• Adapting Foundation Vision-Language Models to Medical Diagnosis via Query-Driven Expert Bridging
• From Prediction to Perfection: Introducing Refinement to Autoregressive Image Generation
• Your Offline Policy is Not Trustworthy: Bilevel Reinforcement Learning for Sequential Portfolio Optimization
• Mamba-Adaptor: State Space Model Adaptor for Visual Recognition
• Adversarial Robustness for Unified Multi-Modal Encoders via Efficient Calibration

Related

• Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification
• Attn-Adapter: Attention Is All You Need for Online Few-shot Learner of Vision-Language Model
• Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling
• CLIP's Visual Embedding Projector is a Few-shot Cornucopia
• SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification