Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision

• URL: http://arxiv.org/abs/2309.14181v3
• Date: Mon, 1 Jan 2024 14:48:48 GMT
• Title: Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision
• Authors: Haoning Wu, Zicheng Zhang, Erli Zhang, Chaofeng Chen, Liang Liao, Annan Wang, Chunyi Li, Wenxiu Sun, Qiong Yan, Guangtao Zhai, Weisi Lin
• Abstract summary: Multi-modality Large Language Models (MLLMs) have catalyzed a shift in computer vision from specialized models to general-purpose foundation models. We present Q-Bench, a holistic benchmark crafted to evaluate potential abilities of MLLMs on three realms: low-level visual perception, low-level visual description, and overall visual quality assessment.
• Score: 85.6008224440157
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The rapid evolution of Multi-modality Large Language Models (MLLMs) has catalyzed a shift in computer vision from specialized models to general-purpose foundation models. Nevertheless, there is still an inadequacy in assessing the abilities of MLLMs on low-level visual perception and understanding. To address this gap, we present Q-Bench, a holistic benchmark crafted to systematically evaluate potential abilities of MLLMs on three realms: low-level visual perception, low-level visual description, and overall visual quality assessment. a) To evaluate the low-level perception ability, we construct the LLVisionQA dataset, consisting of 2,990 diverse-sourced images, each equipped with a human-asked question focusing on its low-level attributes. We then measure the correctness of MLLMs on answering these questions. b) To examine the description ability of MLLMs on low-level information, we propose the LLDescribe dataset consisting of long expert-labelled golden low-level text descriptions on 499 images, and a GPT-involved comparison pipeline between outputs of MLLMs and the golden descriptions. c) Besides these two tasks, we further measure their visual quality assessment ability to align with human opinion scores. Specifically, we design a softmax-based strategy that enables MLLMs to predict quantifiable quality scores, and evaluate them on various existing image quality assessment (IQA) datasets. Our evaluation across the three abilities confirms that MLLMs possess preliminary low-level visual skills. However, these skills are still unstable and relatively imprecise, indicating the need for specific enhancements on MLLMs towards these abilities. We hope that our benchmark can encourage the research community to delve deeper to discover and enhance these untapped potentials of MLLMs. Project Page: https://q-future.github.io/Q-Bench.

Related papers

• Eyes Can Deceive: Benchmarking Counterfactual Reasoning Abilities of Multi-modal Large Language Models [71.34097831618631]
  We introduce a novel textbfCountertextbfFactual textbfMultitextbfModal reasoning benchmark, abbreviated as textbfCFMM. Our CFMM comprises six challenging tasks, each including hundreds of carefully human-labeled counterfactual questions. We find that existing MLLMs prefer to believe what they see, but ignore the counterfactual presuppositions presented in the question.
  arXiv  Detail & Related papers  (2024-04-19T15:53:27Z)
• A Benchmark for Multi-modal Foundation Models on Low-level Vision: from Single Images to Pairs [76.24832641793621]
  We design benchmark settings to emulate human language responses related to low-level vision. We extend the low-level perception-related question-answering and description evaluations of MLLMs from single images to image pairs. We demonstrate that several MLLMs have decent low-level visual competencies on single images, but only GPT-4V exhibits higher accuracy on pairwise comparisons than humans.
  arXiv  Detail & Related papers  (2024-02-11T06:44:11Z)
• MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark [41.68821233828375]
  This paper introduces a novel benchmark, termed MLLM-as-a-Judge, to assess the ability of MLLMs in assisting judges across diverse modalities. Our study reveals that, while MLLMs demonstrate remarkable human-like discernment in Pair Comparison, there is a significant divergence from human preferences in Scoring Evaluation and Batch Ranking.
  arXiv  Detail & Related papers  (2024-02-07T12:28:32Z)
• MM-SAP: A Comprehensive Benchmark for Assessing Self-Awareness of Multimodal Large Language Models in Perception [21.60103376506254]
  Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in visual perception and understanding. These models also suffer from hallucinations, which limit their reliability as AI systems. This paper aims to define and evaluate the self-awareness of MLLMs in perception.
  arXiv  Detail & Related papers  (2024-01-15T08:19:22Z)
• Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels [95.44077384918725]
  We propose to teach large multi-modality models (LMMs) with text-defined rating levels instead of scores. The proposed Q-Align achieves state-of-the-art performance on image quality assessment (IQA), image aesthetic assessment (IAA) and video quality assessment (VQA) tasks.
  arXiv  Detail & Related papers  (2023-12-28T16:10:25Z)
• Q-Boost: On Visual Quality Assessment Ability of Low-level Multi-Modality Foundation Models [80.79438689784958]
  We introduce Q-Boost, a strategy designed to enhance low-level MLLMs in image quality assessment (IQA) and video quality assessment (VQA) tasks. Q-Boost innovates by incorporating a middle ground' approach through $neutral$ prompts, allowing for a more balanced and detailed assessment. The experimental results show that the low-level MLLMs exhibit outstanding zeros-shot performance on the IQA/VQA tasks equipped with the Q-Boost strategy.
  arXiv  Detail & Related papers  (2023-12-23T17:02:25Z)
• 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)

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.