Exploring the Transferability of Visual Prompting for Multimodal Large Language Models
- URL: http://arxiv.org/abs/2404.11207v1
- Date: Wed, 17 Apr 2024 09:39:07 GMT
- Title: Exploring the Transferability of Visual Prompting for Multimodal Large Language Models
- Authors: Yichi Zhang, Yinpeng Dong, Siyuan Zhang, Tianzan Min, Hang Su, Jun Zhu,
- Abstract summary: Transferable Visual Prompting (TVP) is a simple and effective approach to generate visual prompts that can transfer to different models and improve their performance on downstream tasks after trained on only one model.
We introduce two strategies to address the issue of cross-model feature corruption of existing visual prompting methods and enhance the transferability of the learned prompts.
- Score: 47.162575147632396
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Although Multimodal Large Language Models (MLLMs) have demonstrated promising versatile capabilities, their performance is still inferior to specialized models on downstream tasks, which makes adaptation necessary to enhance their utility. However, fine-tuning methods require independent training for every model, leading to huge computation and memory overheads. In this paper, we propose a novel setting where we aim to improve the performance of diverse MLLMs with a group of shared parameters optimized for a downstream task. To achieve this, we propose Transferable Visual Prompting (TVP), a simple and effective approach to generate visual prompts that can transfer to different models and improve their performance on downstream tasks after trained on only one model. We introduce two strategies to address the issue of cross-model feature corruption of existing visual prompting methods and enhance the transferability of the learned prompts, including 1) Feature Consistency Alignment: which imposes constraints to the prompted feature changes to maintain task-agnostic knowledge; 2) Task Semantics Enrichment: which encourages the prompted images to contain richer task-specific semantics with language guidance. We validate the effectiveness of TVP through extensive experiments with 6 modern MLLMs on a wide variety of tasks ranging from object recognition and counting to multimodal reasoning and hallucination correction.
Related papers
- Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment [58.94611347128066]
Task Preference Optimization (TPO) is a novel method that utilizes differentiable task preferences derived from typical fine-grained visual tasks.
By leveraging rich visual labels during training, TPO significantly enhances the MLLM's multimodal capabilities and task-specific performance.
Our instantiation of this approach with VideoChat and LLaVA demonstrates an overall 14.6% improvement in multimodal performance compared to baseline models.
arXiv Detail & Related papers (2024-12-26T18:56:05Z) - ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning [38.26304604660713]
ADEM-VL is an efficient vision-language method that tunes models based on pretrained large language models.
Our framework surpasses existing methods by an average accuracy of 0.77% on ScienceQA dataset.
arXiv Detail & Related papers (2024-10-23T11:31:06Z) - VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks [89.24440488456405]
VisionLLM v2 is an end-to-end generalist multimodal large model (MLLM)
It unifies visual perception, understanding, and generation within a single framework.
arXiv Detail & Related papers (2024-06-12T16:44:50Z) - NoteLLM-2: Multimodal Large Representation Models for Recommendation [71.87790090964734]
Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks.
Their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains underexplored.
We propose an end-to-end fine-tuning method that customizes the integration of any existing LLMs and vision encoders for efficient multimodal representation.
arXiv Detail & Related papers (2024-05-27T03:24:01Z) - Meta-Task Prompting Elicits Embeddings from Large Language Models [54.757445048329735]
We introduce a new unsupervised text embedding method, Meta-Task Prompting with Explicit One-Word Limitation.
We generate high-quality sentence embeddings from Large Language Models without the need for model fine-tuning.
Our findings suggest a new scaling law, offering a versatile and resource-efficient approach for embedding generation across diverse scenarios.
arXiv Detail & Related papers (2024-02-28T16:35:52Z) - Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond [16.913115978881866]
We propose a framework for unified task embeddings (FUTE), task embeddings from various models, including smaller language models and Large Language Models with varied prompts, within a single vector space.
Such uniformity enables comparison and analysis of similarities amongst different models, broadening the scope and utility of existing task embedding methods in multi-model scenarios.
arXiv Detail & Related papers (2024-02-22T13:13:31Z) - Multi-Modal Few-Shot Temporal Action Detection [157.96194484236483]
Few-shot (FS) and zero-shot (ZS) learning are two different approaches for scaling temporal action detection to new classes.
We introduce a new multi-modality few-shot (MMFS) TAD problem, which can be considered as a marriage of FS-TAD and ZS-TAD.
arXiv Detail & Related papers (2022-11-27T18:13:05Z) - HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both
Language and Vision-and-Language Tasks [38.43269863509866]
How to perform parameter-efficient fine-tuning has become fairly important for quick transfer learning and deployment.
We design a novel unified parameter-efficient transfer learning framework that works effectively on both pure language and V&L tasks.
Our proposed framework adds fewer trainable parameters in multi-task learning while achieving superior performances and transfer ability compared to state-of-the-art methods.
arXiv Detail & Related papers (2022-03-08T06:51:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.