Visually Descriptive Language Model for Vector Graphics Reasoning

• URL: http://arxiv.org/abs/2404.06479v4
• Date: Thu, 03 Oct 2024 21:59:32 GMT
• Title: Visually Descriptive Language Model for Vector Graphics Reasoning
• Authors: Zhenhailong Wang, Joy Hsu, Xingyao Wang, Kuan-Hao Huang, Manling Li, Jiajun Wu, Heng Ji,
• Abstract summary: We propose the Visually Descriptive Language Model (VDLM) to bridge the gap between low-level visual perception and high-level language reasoning. We show that VDLM significantly improves state-of-the-art LMMs like GPT-4o on various multimodal perception and reasoning tasks.
• Score: 76.42082386029206
• License:
• Abstract: Despite significant advancements, large multimodal models (LMMs) still struggle to bridge the gap between low-level visual perception -- focusing on shapes, sizes, and layouts -- and high-level language reasoning, such as semantics and logic. This limitation is evident in tasks that require precise visual perception, like comparing geometric properties or solving visual reasoning problems. To study this failure mode, we focus on vector graphics -- images composed of 2D objects and shapes, prevalent in LMM-based tasks in web, design, and OS environments. We identify two key research questions: how can we enable precise visual perception, and how can we facilitate high-level reasoning based on such low-level perceptions? To capture fine visual details, we use Scalable Vector Graphics (SVG) for accurate encoding of visual scenes. However, SVGs are not readily interpretable by LMMs in a zero-shot manner. To tackle this, we propose the Visually Descriptive Language Model (VDLM), which introduces a Primal Visual Description (PVD) as an intermediate textual representation. PVD translates SVGs into a text-based abstraction consisting of primitive attributes (e.g., shape, position, measurement) and their corresponding values. PVD can be learned using task-agnostic synthesized data and represents visual primitives that are universal across vector graphics. This abstraction is more structured, allowing for direct interpretation by foundation models for zero-shot generalization. Without human-annotated data, empirical results show that VDLM significantly improves state-of-the-art LMMs like GPT-4o on various multimodal perception and reasoning tasks. Extensive analyses of VDLM show improved interpretability due to its disentangled perception and reasoning. We also demonstrate a positive correlation between PVD quality and task performance. Project page: https://mikewangwzhl.github.io/VDLM/

Related papers

• Improving the Efficiency of Visually Augmented Language Models [5.948051066733892]
  This paper shows that explicit images are not necessary to visually augment an LM. Instead, we use visually-grounded text representations obtained from the well-known CLIP multimodal system. We show that BLIND-VALM performs on par with VALM for Visual Language Understanding (VLU), Natural Language Understanding (NLU) and Language Modeling tasks.
  arXiv  Detail & Related papers  (2024-09-17T13:02:19Z)
• 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)
• How Well Can Vision Language Models See Image Details? [53.036922527685064]
  We introduce a pixel value prediction task to explore "How Well Can Vision Language Models See Image Details?" Our research reveals that incorporating pixel value prediction as one of the VLM pre-training tasks and vision encoder adaptation markedly boosts VLM performance on downstream image-language understanding tasks.
  arXiv  Detail & Related papers  (2024-08-07T17:59:40Z)
• VGBench: Evaluating Large Language Models on Vector Graphics Understanding and Generation [28.1277394934428]
  VGBench is a comprehensive benchmark for Large Language Models (LLMs) on handling vector graphics. LLMs show strong capability on both aspects while exhibiting less desirable performance on low-level formats (SVG)
  arXiv  Detail & Related papers  (2024-07-15T17:59:55Z)
• OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding [112.87441334765693]
  OMG-LLaVA is a new framework combining powerful pixel-level vision understanding with reasoning abilities. It can accept various visual and text prompts for flexible user interaction. OMG-LLaVA achieves image-level, object-level, and pixel-level reasoning and understanding in a single model.
  arXiv  Detail & Related papers  (2024-06-27T17:59:01Z)
• GeoVLN: Learning Geometry-Enhanced Visual Representation with Slot Attention for Vision-and-Language Navigation [52.65506307440127]
  We propose GeoVLN, which learns Geometry-enhanced visual representation based on slot attention for robust Visual-and-Language Navigation. We employ V&L BERT to learn a cross-modal representation that incorporate both language and vision informations.
  arXiv  Detail & Related papers  (2023-05-26T17:15:22Z)
• Jointly Visual- and Semantic-Aware Graph Memory Networks for Temporal Sentence Localization in Videos [67.12603318660689]
  We propose a novel Hierarchical Visual- and Semantic-Aware Reasoning Network (HVSARN) HVSARN enables both visual- and semantic-aware query reasoning from object-level to frame-level. Experiments on three datasets demonstrate that our HVSARN achieves a new state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-03-02T08:00:22Z)
• Understanding ME? Multimodal Evaluation for Fine-grained Visual Commonsense [98.70218717851665]
  It is unclear whether the models really understand the visual scene and underlying commonsense knowledge due to limited evaluation data resources. We present a Multimodal Evaluation (ME) pipeline to automatically generate question-answer pairs to test models' understanding of the visual scene, text, and related knowledge. We then take a step further to show that training with the ME data boosts the model's performance in standard VCR evaluation.
  arXiv  Detail & Related papers  (2022-11-10T21:44:33Z)

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.