Learning to Ground VLMs without Forgetting
- URL: http://arxiv.org/abs/2410.10491v1
- Date: Mon, 14 Oct 2024 13:35:47 GMT
- Title: Learning to Ground VLMs without Forgetting
- Authors: Aritra Bhowmik, Mohammad Mahdi Derakhshani, Dennis Koelma, Martin R. Oswald, Yuki M. Asano, Cees G. M. Snoek,
- Abstract summary: We introduce LynX, a framework that equips pretrained Visual Language Models with visual grounding ability without forgetting their existing image and language understanding skills.
To train the model effectively, we generate a high-quality synthetic dataset we call SCouT, which mimics human reasoning in visual grounding.
We evaluate LynX on several object detection and visual grounding datasets, demonstrating strong performance in object detection, zero-shot localization and grounded reasoning.
- Score: 54.033346088090674
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Spatial awareness is key to enable embodied multimodal AI systems. Yet, without vast amounts of spatial supervision, current Visual Language Models (VLMs) struggle at this task. In this paper, we introduce LynX, a framework that equips pretrained VLMs with visual grounding ability without forgetting their existing image and language understanding skills. To this end, we propose a Dual Mixture of Experts module that modifies only the decoder layer of the language model, using one frozen Mixture of Experts (MoE) pre-trained on image and language understanding and another learnable MoE for new grounding capabilities. This allows the VLM to retain previously learned knowledge and skills, while acquiring what is missing. To train the model effectively, we generate a high-quality synthetic dataset we call SCouT, which mimics human reasoning in visual grounding. This dataset provides rich supervision signals, describing a step-by-step multimodal reasoning process, thereby simplifying the task of visual grounding. We evaluate LynX on several object detection and visual grounding datasets, demonstrating strong performance in object detection, zero-shot localization and grounded reasoning while maintaining its original image and language understanding capabilities on seven standard benchmark datasets.
Related papers
- Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models [127.38740043393527]
We propose ViFT, a visual instruction-free fine-tuning framework for LVLMs.
We only require the text-only instructions and image caption data during training, to separately learn the task-solving and visual perception abilities.
Experimental results demonstrate that ViFT can achieve state-of-the-art performance on several visual reasoning and visual instruction following benchmarks.
arXiv Detail & Related papers (2025-02-17T04:38:12Z) - EAGLE: Enhanced Visual Grounding Minimizes Hallucinations in Instructional Multimodal Models [54.234657224615354]
Large language models and vision transformers have demonstrated impressive zero-shot capabilities, enabling significant transferability in downstream tasks.
Despite incorporating vast image and language pre-training, these multi-modal architectures often generate responses that deviate from the ground truth in the image data.
Current methods for mitigating hallucinations generally focus on regularizing the language component, improving the fusion module, or ensembling multiple visual encoders to improve visual representation.
We show that a straightforward reformulation of the original contrastive pre-training task results in an improved visual encoder that can be incorporated into the instructional multi-modal architecture without additional instructional training.
arXiv Detail & Related papers (2025-01-06T00:39:31Z) - FiVL: A Framework for Improved Vision-Language Alignment [10.184567639685321]
We introduce FiVL, a novel method for constructing datasets designed to train LVLMs for enhanced visual grounding.
These datasets can be utilized for both training and assessing an LVLM's ability to use image content as substantive evidence.
To demonstrate the utility of our dataset, we introduce an innovative training task that outperforms baselines alongside a validation method and application for explainability.
arXiv Detail & Related papers (2024-12-19T09:24:10Z) - Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities [30.176918208200604]
Vision-Language Models (VLMs) have emerged as general purpose tools for addressing a variety of complex computer vision problems.
These models have been shown to be highly capable, but also lacking some basic visual understanding skills.
This paper sets out to understand the limitations of SoTA VLMs on fundamental visual tasks.
arXiv Detail & Related papers (2024-08-13T08:26:32Z) - Learning Visual Grounding from Generative Vision and Language Model [29.2712567454021]
Visual grounding tasks aim to localize image regions based on natural language references.
We find that grounding knowledge already exists in generative VLM and can be elicited by proper prompting.
Our results demonstrate the promise of generative VLM to scale up visual grounding in the real world.
arXiv Detail & Related papers (2024-07-18T20:29:49Z) - Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs [61.143381152739046]
We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach.
Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations.
We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes.
arXiv Detail & Related papers (2024-06-24T17:59:42Z) - Improving Visual Commonsense in Language Models via Multiple Image Generation [41.565399860320966]
Existing large language models (LLMs) are primarily trained using textual data only.
Visual Language Models, which excel at visually-oriented tasks, often fail at non-visual tasks such as basic commonsense reasoning.
This divergence highlights a critical challenge - the integration of robust visual understanding with foundational text-based language reasoning.
arXiv Detail & Related papers (2024-06-19T15:17:10Z) - ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension [71.03445074045092]
We propose ClawMachine, offering a new methodology that explicitly notates each entity using token collectives groups of visual tokens.
Our method unifies the prompt and answer of visual referential tasks without using additional syntax.
ClawMachine achieves superior performance on scene-level and referential understanding tasks with higher efficiency.
arXiv Detail & Related papers (2024-06-17T08:39:16Z) - VCoder: Versatile Vision Encoders for Multimodal Large Language Models [46.95488342139727]
Multimodal Large Language Models (MLLM) have recently achieved impressive performance on vision-language tasks.
However, when prompted to identify or count (perceive) the entities in a given image, existing MLLM systems fail.
We propose using Versatile vision enCoders (VCoder) as perception eyes for Multimodal LLMs.
arXiv Detail & Related papers (2023-12-21T18:49:47Z) - Large Language Models are Visual Reasoning Coordinators [144.67558375045755]
We propose a novel paradigm that coordinates multiple vision-language models for visual reasoning.
We show that our instruction tuning variant, Cola-FT, achieves state-of-the-art performance on visual question answering.
We also show that our in-context learning variant, Cola-Zero, exhibits competitive performance in zero and few-shot settings.
arXiv Detail & Related papers (2023-10-23T17:59:31Z)
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.