Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs

• URL: http://arxiv.org/abs/2501.04670v2
• Date: Fri, 31 Jan 2025 16:12:22 GMT
• Title: Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs
• Authors: Yikang Zhou, Tao Zhang, Shilin Xu, Shihao Chen, Qianyu Zhou, Yunhai Tong, Shunping Ji, Jiangning Zhang, Xiangtai Li, Lu Qi,
• Abstract summary: We construct a benchmark to fairly benchmark over 30 different MLLMs. We present CoLVA, a novel contrastive MLLM with object-level contrastive learning and instruction augmentation strategy. Results show that CoLVA achieves 51.06% overall accuracy (OA) on the MMVM benchmark, surpassing GPT-4o and baseline by 8.41% and 23.58% OA, respectively.
• Score: 42.57007182613631
• License:
• Abstract: Recent advancements in multimodal models have shown a strong ability in visual perception, reasoning abilities, and vision-language understanding. However, studies on visual matching ability are missing, where finding the visual correspondence of objects is essential in vision research. Our research reveals that the matching capabilities in recent multimodal LLMs (MLLMs) still exhibit systematic shortcomings, even with current strong MLLMs models, GPT-4o. In particular, we construct a Multimodal Visual Matching (MMVM) benchmark to fairly benchmark over 30 different MLLMs. The MMVM benchmark is built from 15 open-source datasets and Internet videos with manual annotation. We categorize the data samples of MMVM benchmark into eight aspects based on the required cues and capabilities to more comprehensively evaluate and analyze current MLLMs. In addition, we have designed an automatic annotation pipeline to generate the MMVM SFT dataset, including 220K visual matching data with reasoning annotation. Finally, we present CoLVA, a novel contrastive MLLM with two novel technical designs: fine-grained vision expert with object-level contrastive learning and instruction augmentation strategy. CoLVA achieves 51.06\% overall accuracy (OA) on the MMVM benchmark, surpassing GPT-4o and baseline by 8.41\% and 23.58\% OA, respectively. The results show the effectiveness of our MMVM SFT dataset and our novel technical designs. Code, benchmark, dataset, and models are available at https://github.com/zhouyiks/CoLVA.

Related papers

• MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning [44.497776004372724]
  Multi-modal large language models (MLLMs) have made significant strides in various visual understanding tasks. We present MG-LLaVA, an innovative MLLM that enhances the model's visual processing capabilities by incorporating a multi-granularity vision flow. To further refine the model's object recognition abilities, we incorporate object-level features derived from bounding boxes identified by offline detectors.
  arXiv  Detail & Related papers  (2024-06-25T17:55:11Z)
• MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs [38.93090238335506]
  Spurious bias, a tendency to use spurious correlations between non-essential input attributes and target variables for predictions, has revealed a severe pitfall in deep learning models trained on single modality data. We introduce MM-SpuBench, a comprehensive visual question-answering (VQA) benchmark designed to evaluate MLLMs' reliance on nine distinct categories of spurious correlations. Our findings illuminate the persistence of the reliance on spurious correlations from these models and underscore the urge for new methodologies to mitigate spurious biases.
  arXiv  Detail & Related papers  (2024-06-24T20:29:16Z)
• 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)
• MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs [88.28014831467503]
  We introduce MMDU, a comprehensive benchmark, and MMDU-45k, a large-scale instruction tuning dataset. MMDU has a maximum of 18k image+text tokens, 20 images, and 27 turns, which is at least 5x longer than previous benchmarks. We demonstrate that ffne-tuning open-source LVLMs on MMDU-45k signiffcantly address this gap, generating longer and more accurate conversations.
  arXiv  Detail & Related papers  (2024-06-17T17:59:47Z)
• Are We on the Right Way for Evaluating Large Vision-Language Models? [92.5761176224556]
  Large vision-language models (LVLMs) have recently achieved rapid progress, sparking numerous studies to evaluate their multi-modal capabilities. We identify two primary issues: Visual content is unnecessary for many samples and intentional data leakage exists. We present MMStar, an elite vision-indispensable multi-modal benchmark comprising 1,500 samples meticulously selected by humans.
  arXiv  Detail & Related papers  (2024-03-29T17:59:34Z)
• COCO is "ALL'' You Need for Visual Instruction Fine-tuning [39.438410070172125]
  Visual instruction fine-tuning (IFT) is a vital process for aligning MLLMs' output with user's intentions. Recent studies propose to construct visual IFT datasets through a multifaceted approach. We establish a new IFT dataset, with images sourced from the COCO dataset along with more diverse instructions.
  arXiv  Detail & Related papers  (2024-01-17T04:43:45Z)
• SEED-Bench-2: Benchmarking Multimodal Large Language Models [67.28089415198338]
  Multimodal large language models (MLLMs) have recently demonstrated exceptional capabilities in generating not only texts but also images given interleaved multimodal inputs. SEED-Bench-2 comprises 24K multiple-choice questions with accurate human annotations, which spans 27 dimensions. We evaluate the performance of 23 prominent open-source MLLMs and summarize valuable observations.
  arXiv  Detail & Related papers  (2023-11-28T05:53:55Z)
• MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models [73.86954509967416]
  Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks. This paper presents the first comprehensive MLLM Evaluation benchmark MME. It measures both perception and cognition abilities on a total of 14 subtasks.
  arXiv  Detail & Related papers  (2023-06-23T09:22:36Z)

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.