Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation

• URL: http://arxiv.org/abs/2409.15125v1
• Date: Mon, 23 Sep 2024 15:31:25 GMT
• Title: Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation
• Authors: Manu Gaur, Darshan Singh S, Makarand Tapaswi,
• Abstract summary: We evaluate how well an MLLM understands a specific visual concept by its ability to uniquely describe two extremely similar images. We curate 247 highly similar image pairs as part of the D3 benchmark. For each image pair, the model is prompted to: (1) Detect a specific visual difference, and (2) Describe the target image uniquely such that it (3) Discriminates the target image from the distractor.
• Score: 13.311411816150551
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Visual Question Answering (VQA) with multiple choice questions enables a vision-centric evaluation of Multimodal Large Language Models (MLLMs). Although it reliably checks the existence of specific visual abilities, it is easier for the model to select an answer from multiple choices (VQA evaluation) than to generate the answer itself. In this work, we offer a novel perspective: we evaluate how well an MLLM understands a specific visual concept by its ability to uniquely describe two extremely similar images that differ only in the targeted visual concept. Specifically, we assess the ability of MLLMs to capture specific points of visual differences using self-retrieval, i.e., by retrieving the target image using its generated caption against the other image in the pair serving as the distractor. We curate 247 highly similar image pairs as part of the D3 benchmark. For each image pair, the model is prompted to: (1) Detect a specific visual difference, and (2) Describe the target image uniquely such that it (3) Discriminates the target image from the distractor. Self-retrieval within D3 enables whitebox evaluation across six different visual patterns, revealing that current models struggle to independently discern fine-grained visual differences, with open-source models failing to outperform random guess.

Related papers

• VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs [18.349695067647012]
  Visual Language Models excel at complex visual tasks such as VQA and chart understanding, yet recent work suggests they struggle with simple tests.<n>We present an evaluation that tests vision-language models' capacity for nonlocal visual reasoning.<n>Our findings show that despite gains in raw visual acuity, current models lack core visual reasoning capabilities.
  arXiv  Detail & Related papers  (2025-07-04T23:15:52Z)
• MiCo: Multi-image Contrast for Reinforcement Visual Reasoning [72.81576836419373]
  Chain-of-Thought (CoT) reasoning can be used to link visual cues across multiple images.<n>We adapt rule-based reinforcement learning for Vision-Language Models (VLMs)<n>Our method achieves significant improvements on multi-image reasoning benchmarks and shows strong performance on general vision tasks.
  arXiv  Detail & Related papers  (2025-06-27T17:59:27Z)
• BYO-Eval: Build Your Own Dataset for Fine-Grained Visual Assessment of Multimodal Language Models [2.526146573337397]
  We propose a new evaluation methodology, inspired by ophthalmologic diagnostics.<n>We use procedural generation of synthetic images to obtain control over visual attributes.<n>This diagnostic allows systematic stress testing and fine-grained failure analysis.
  arXiv  Detail & Related papers  (2025-06-05T12:43:10Z)
• 3D Question Answering via only 2D Vision-Language Models [87.41421075243103]
  Large vision-language models (LVLMs) have advanced numerous fields.<n>We explore how to harness their potential to address 3D scene understanding tasks, using 3D question answering (3D-QA) as a representative example.<n>Specifically, we sample 2D views from a 3D point cloud and feed them into 2D models to answer a given question.<n>We propose cdViews, a novel approach to automatically selecting critical and diverse Views for 3D-QA.
  arXiv  Detail & Related papers  (2025-05-28T09:04:39Z)
• See or Recall: A Sanity Check for the Role of Vision in Solving Visualization Question Answer Tasks with Multimodal LLMs [13.330105502094721]
  How an MLLM perceives and reasons about visualizations can be fundamentally different from how humans approach the same problem. We propose a comprehensive sanity check framework that integrates a rule-based decision tree and a sanity check table.
  arXiv  Detail & Related papers  (2025-04-14T02:19:28Z)
• From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment [51.3011761744484]
  Multi-modal Large language models can only process a finite number of frames in a single inference. We propose multiple predictions through visual context sampling, followed by a scoring mechanism to select the final prediction. Experiments show that this approach covers the correct answer for a high percentage of long video questions.
  arXiv  Detail & Related papers  (2025-03-26T11:53:03Z)
• Matryoshka Multimodal Models [92.41824727506751]
  We propose M3: Matryoshka Multimodal Models, which learns to represent visual content as nested sets of visual tokens. We find that COCO-style benchmarks only need around 9 visual tokens to obtain accuracy similar to that of using all 576 tokens.
  arXiv  Detail & Related papers  (2024-05-27T17:59:56Z)
• PEVA-Net: Prompt-Enhanced View Aggregation Network for Zero/Few-Shot Multi-View 3D Shape Recognition [8.15444057380305]
  We focus on exploiting the large vision-language model, i.e., CLIP, to address zero/few-shot 3D shape recognition. We propose Prompt-Enhanced View Aggregation Network (PEVA-Net) to simultaneously address zero/few-shot 3D shape recognition.
  arXiv  Detail & Related papers  (2024-04-30T00:16:59Z)
• Q-Bench+: A Benchmark for Multi-modal Foundation Models on Low-level Vision from Single Images to Pairs [71.07108539262721]
  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)
• Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models [59.05769810380928]
  Rephrase, Augment and Reason (RepARe) is a gradient-free framework that extracts salient details about the image using the underlying vision-language model. We show that RepARe can result in a 3.85% (absolute) increase in zero-shot accuracy on VQAv2, 6.41%, and 7.94% points increase on A-OKVQA, and VizWiz respectively.
  arXiv  Detail & Related papers  (2023-10-09T16:57:57Z)
• LOIS: Looking Out of Instance Semantics for Visual Question Answering [17.076621453814926]
  We propose a model framework without bounding boxes to understand the causal nexus of object semantics in images. We implement a mutual relation attention module to model sophisticated and deeper visual semantic relations between instance objects and background information. Our proposed attention model can further analyze salient image regions by focusing on important word-related questions.
  arXiv  Detail & Related papers  (2023-07-26T12:13:00Z)
• Zero-shot Model Diagnosis [80.36063332820568]
  A common approach to evaluate deep learning models is to build a labeled test set with attributes of interest and assess how well it performs. This paper argues the case that Zero-shot Model Diagnosis (ZOOM) is possible without the need for a test set nor labeling.
  arXiv  Detail & Related papers  (2023-03-27T17:59:33Z)
• Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective [93.56647950778357]
  Blind image quality assessment (BIQA) predicts the human perception of image quality without any reference information. We develop a general and automated multitask learning scheme for BIQA to exploit auxiliary knowledge from other tasks.
  arXiv  Detail & Related papers  (2023-03-27T07:58:09Z)
• MERLOT: Multimodal Neural Script Knowledge Models [74.05631672657452]
  We introduce MERLOT, a model that learns multimodal script knowledge by watching millions of YouTube videos with transcribed speech. MERLOT exhibits strong out-of-the-box representations of temporal commonsense, and achieves state-of-the-art performance on 12 different video QA datasets. On Visual Commonsense Reasoning, MERLOT answers questions correctly with 80.6% accuracy, outperforming state-of-the-art models of similar size by over 3%.
  arXiv  Detail & Related papers  (2021-06-04T17:57:39Z)
• Analysis on Image Set Visual Question Answering [0.3359875577705538]
  We tackle the challenge of Visual Question Answering in multi-image setting. Traditional VQA tasks have focused on a single-image setting where the target answer is generated from a single image. In this report, we work with 4 approaches in a bid to improve the performance on the task.
  arXiv  Detail & Related papers  (2021-03-31T20:47:32Z)

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.