Imperfect Vision Encoders: Efficient and Robust Tuning for Vision-Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Panos, Aristeidis, Aljundi, Rahaf, Reino, Daniel Olmeda, Turner, Richard E
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929432847974400
author Panos, Aristeidis
Aljundi, Rahaf
Reino, Daniel Olmeda
Turner, Richard E
author_facet Panos, Aristeidis
Aljundi, Rahaf
Reino, Daniel Olmeda
Turner, Richard E
contents Vision language models (VLMs) demonstrate impressive capabilities in visual question answering and image captioning, acting as a crucial link between visual and language models. However, existing open-source VLMs heavily rely on pretrained and frozen vision encoders (such as CLIP). Despite CLIP's robustness across diverse domains, it still exhibits non-negligible image understanding errors. These errors propagate to the VLM responses, resulting in sub-optimal performance. In our work, we propose an efficient and robust method for updating vision encoders within VLMs. Our approach selectively and locally updates encoders, leading to substantial performance improvements on data where previous mistakes occurred, while maintaining overall robustness. Furthermore, we demonstrate the effectiveness of our method during continual few-shot updates. Theoretical grounding, generality, and computational efficiency characterize our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16526
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Imperfect Vision Encoders: Efficient and Robust Tuning for Vision-Language Models
Panos, Aristeidis
Aljundi, Rahaf
Reino, Daniel Olmeda
Turner, Richard E
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Vision language models (VLMs) demonstrate impressive capabilities in visual question answering and image captioning, acting as a crucial link between visual and language models. However, existing open-source VLMs heavily rely on pretrained and frozen vision encoders (such as CLIP). Despite CLIP's robustness across diverse domains, it still exhibits non-negligible image understanding errors. These errors propagate to the VLM responses, resulting in sub-optimal performance. In our work, we propose an efficient and robust method for updating vision encoders within VLMs. Our approach selectively and locally updates encoders, leading to substantial performance improvements on data where previous mistakes occurred, while maintaining overall robustness. Furthermore, we demonstrate the effectiveness of our method during continual few-shot updates. Theoretical grounding, generality, and computational efficiency characterize our approach.
title Imperfect Vision Encoders: Efficient and Robust Tuning for Vision-Language Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2407.16526