Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis
This work addresses the problem of improving image captioning for AI and computer vision researchers by analyzing the adaptability of multimodal LLMs, but it is incremental as it builds on existing models and methods.
The paper investigated whether multimodal large language models (LLMs) like GPT-4V and Gemini can replace traditional image captioning networks by evaluating their zero-shot performance and fine-tuning adaptability on benchmarks, finding that while zero-shot results are impressive, fine-tuning for specific domains without losing generalization is challenging.
The task of image captioning demands an algorithm to generate natural language descriptions of visual inputs. Recent advancements have seen a convergence between image captioning research and the development of Large Language Models (LLMs) and Multimodal LLMs -- like GPT-4V and Gemini -- which extend the capabilities of text-only LLMs to multiple modalities. This paper investigates whether Multimodal LLMs can supplant traditional image captioning networks by evaluating their performance on various image description benchmarks. We explore both the zero-shot capabilities of these models and their adaptability to different semantic domains through fine-tuning methods, including prompt learning, prefix tuning, and low-rank adaptation. Our results demonstrate that while Multimodal LLMs achieve impressive zero-shot performance, fine-tuning for specific domains while maintaining their generalization capabilities intact remains challenging. We discuss the implications of these findings for future research in image captioning and the development of more adaptable Multimodal LLMs.