CVMar 12, 2024

Beyond Text: Frozen Large Language Models in Visual Signal Comprehension

arXiv:2403.07874v134 citationsh-index: 7Has CodeCVPR
Originality Incremental advance
AI Analysis

This addresses the challenge of multi-modal AI integration for researchers and practitioners by allowing frozen LLMs to process visual data, though it is incremental as it builds on existing models like CLIP.

The paper tackles the problem of enabling large language models (LLMs) to comprehend visual signals without fine-tuning by introducing a Vision-to-Language Tokenizer that translates images into discrete words from the LLM's vocabulary, achieving capabilities in tasks like image recognition, captioning, and denoising.

In this work, we investigate the potential of a large language model (LLM) to directly comprehend visual signals without the necessity of fine-tuning on multi-modal datasets. The foundational concept of our method views an image as a linguistic entity, and translates it to a set of discrete words derived from the LLM's vocabulary. To achieve this, we present the Vision-to-Language Tokenizer, abbreviated as V2T Tokenizer, which transforms an image into a ``foreign language'' with the combined aid of an encoder-decoder, the LLM vocabulary, and a CLIP model. With this innovative image encoding, the LLM gains the ability not only for visual comprehension but also for image denoising and restoration in an auto-regressive fashion-crucially, without any fine-tuning. We undertake rigorous experiments to validate our method, encompassing understanding tasks like image recognition, image captioning, and visual question answering, as well as image denoising tasks like inpainting, outpainting, deblurring, and shift restoration. Code and models are available at https://github.com/zh460045050/V2L-Tokenizer.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes