Instruction-Guided Visual Masking
- URL: http://arxiv.org/abs/2405.19783v2
- Date: Wed, 16 Oct 2024 09:28:22 GMT
- Title: Instruction-Guided Visual Masking
- Authors: Jinliang Zheng, Jianxiong Li, Sijie Cheng, Yinan Zheng, Jiaming Li, Jihao Liu, Yu Liu, Jingjing Liu, Xianyuan Zhan,
- Abstract summary: Instruction-guided Visual Masking (IVM) is a versatile visual grounding model that is compatible with diverse multimodal models.
IVM-enhanced multimodal models can effectively focus on task-relevant image regions to better align with complex instructions.
- Score: 25.26544571379426
- License:
- Abstract: Instruction following is crucial in contemporary LLM. However, when extended to multimodal setting, it often suffers from misalignment between specific textual instruction and targeted local region of an image. To achieve more accurate and nuanced multimodal instruction following, we introduce Instruction-guided Visual Masking (IVM), a new versatile visual grounding model that is compatible with diverse multimodal models, such as LMM and robot model. By constructing visual masks for instruction-irrelevant regions, IVM-enhanced multimodal models can effectively focus on task-relevant image regions to better align with complex instructions. Specifically, we design a visual masking data generation pipeline and create an IVM-Mix-1M dataset with 1 million image-instruction pairs. We further introduce a new learning technique, Discriminator Weighted Supervised Learning (DWSL) for preferential IVM training that prioritizes high-quality data samples. Experimental results on generic multimodal tasks such as VQA and embodied robotic control demonstrate the versatility of IVM, which as a plug-and-play tool, significantly boosts the performance of diverse multimodal models, yielding new state-of-the-art results across challenging multimodal benchmarks. Code, model and data are available at https://github.com/2toinf/IVM.
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) - RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts [17.76606110070648]
We propose RSUniVLM, a unified, end-to-end RS VLM for comprehensive vision understanding across multiple granularity.
RSUniVLM performs effectively in multi-image analysis, with instances of change detection and change captioning.
We also construct a large-scale RS instruction-following dataset based on a variety of existing datasets in both RS and general domain.
arXiv Detail & Related papers (2024-12-07T15:11:21Z) - VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks [60.5257456681402]
We study the potential for building universal embeddings capable of handling a wide range of downstream tasks.
We build a series of VLM2Vec models on SoTA VLMs like Phi-3.5-V, LLaVA-1.6 and evaluate them on MMEB's evaluation split.
Our results show that VLM2Vec achieves an absolute average improvement of 10% to 20% over existing multimodal embedding models.
arXiv Detail & Related papers (2024-10-07T16:14:05Z) - NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks.
We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities.
We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
arXiv Detail & Related papers (2024-09-17T17:59:06Z) - Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model [83.85856356798531]
VistaLLM is a visual system that addresses coarse- and fine-grained vision-language tasks.
It employs a gradient-aware adaptive sampling technique to represent binary segmentation masks as sequences.
We also introduce a novel task, AttCoSeg, which boosts the model's reasoning and grounding capability over multiple input images.
arXiv Detail & Related papers (2023-12-19T18:53:01Z) - u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model [17.3535277338312]
u-LLaVA is an innovative unifying multi-task framework that integrates pixel, regional, and global features to refine the perceptual faculties of MLLMs.
This work contributes a novel mask-based multi-task dataset comprising 277K samples, crafted to challenge and assess the fine-grained perception capabilities of MLLMs.
arXiv Detail & Related papers (2023-11-09T13:18:27Z) - Reformulating Vision-Language Foundation Models and Datasets Towards
Universal Multimodal Assistants [65.47222691674074]
Muffin framework employs pre-trained vision-language models to act as providers of visual signals.
UniMM-Chat dataset explores the complementarities of datasets to generate 1.1M high-quality and diverse multimodal instructions.
arXiv Detail & Related papers (2023-10-01T12:35:18Z) - Position-Enhanced Visual Instruction Tuning for Multimodal Large
Language Models [50.07056960586183]
We propose Position-enhanced Visual Instruction Tuning (PVIT) to extend the functionality of Multimodal Large Language Models (MLLMs)
This integration promotes a more detailed comprehension of images for the MLLM.
We present both quantitative experiments and qualitative analysis that demonstrate the superiority of the proposed model.
arXiv Detail & Related papers (2023-08-25T15:33:47Z)
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.