Pyramid Coder: Hierarchical Code Generator for Compositional Visual Question Answering

• URL: http://arxiv.org/abs/2407.20563v1
• Date: Tue, 30 Jul 2024 05:36:43 GMT
• Title: Pyramid Coder: Hierarchical Code Generator for Compositional Visual Question Answering
• Authors: Ruoyue Shen, Nakamasa Inoue, Koichi Shinoda,
• Abstract summary: Visual question answering (VQA) is the task of providing accurate answers to natural language questions based on visual input. This paper introduces PyramidCoder, a novel prompting framework for PVQA models. Compared to the state-of-the-art PVQA model, our approach improves accuracy by at least 0.5% on the GQA dataset, 1.4% on the VQAv2 dataset, and 2.9% on the NLVR2 dataset.
• Score: 12.399738382728653
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual question answering (VQA) is the task of providing accurate answers to natural language questions based on visual input. Programmatic VQA (PVQA) models have been gaining attention recently. These use large language models (LLMs) to formulate executable programs that address questions requiring complex visual reasoning. However, there are challenges in enabling LLMs to comprehend the usage of image processing modules and generate relevant code. To overcome these challenges, this paper introduces PyramidCoder, a novel prompting framework for PVQA models. PyramidCoder consists of three hierarchical levels, each serving a distinct purpose: query rephrasing, code generation, and answer aggregation. Notably, PyramidCoder utilizes a single frozen LLM and pre-defined prompts at each level, eliminating the need for additional training and ensuring flexibility across various LLM architectures. Compared to the state-of-the-art PVQA model, our approach improves accuracy by at least 0.5% on the GQA dataset, 1.4% on the VQAv2 dataset, and 2.9% on the NLVR2 dataset.

Related papers

• SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization [70.11167263638562]
  Social relation reasoning aims to identify relation categories such as friends, spouses, and colleagues from images. We first present a simple yet well-crafted framework named name, which combines the perception capability of Vision Foundation Models (VFMs) and the reasoning capability of Large Language Models (LLMs) within a modular framework.
  arXiv  Detail & Related papers  (2024-10-28T18:10:26Z)
• Distill Visual Chart Reasoning Ability from LLMs to MLLMs [38.62832112530892]
  Solving complex chart Q&A tasks requires advanced visual reasoning abilities in multimodal large language models (MLLMs) We propose Code-as-Intermediary Translation (CIT), a cost-effective, efficient and easily scalable data synthesis method for distilling visual reasoning abilities from LLMs to MLLMs. We employ text-based synthesizing techniques to construct chart-plotting code and produce ReachQA, a dataset containing 3k reasoning-intensive charts and 20k Q&A pairs.
  arXiv  Detail & Related papers  (2024-10-24T14:50:42Z)
• Trust but Verify: Programmatic VLM Evaluation in the Wild [62.14071929143684]
  Programmatic VLM Evaluation (PROVE) is a new benchmarking paradigm for evaluating VLM responses to open-ended queries. We benchmark the helpfulness-truthfulness trade-offs of a range ofVLMs on PROVE, finding that very few are in-fact able to achieve a good balance between the two.
  arXiv  Detail & Related papers  (2024-10-17T01:19:18Z)
• Declarative Knowledge Distillation from Large Language Models for Visual Question Answering Datasets [9.67464173044675]
  Visual Question Answering (VQA) is the task of answering a question about an image. We present an approach for declarative knowledge distillation from Large Language Models (LLMs) Our results confirm that distilling knowledge from LLMs is in fact a promising direction besides data-driven rule learning approaches.
  arXiv  Detail & Related papers  (2024-10-12T08:17:03Z)
• Revisiting Multi-Modal LLM Evaluation [29.094387692681337]
  We pioneer evaluating recent MLLMs (LLaVA 1.5, LLaVA-NeXT, BLIP2, InstructBLIP, GPT-4V, and GPT-4o) on datasets designed to address weaknesses in earlier ones. Our code is integrated into the widely used LAVIS framework for MLLM evaluation, enabling the rapid assessment of future MLLMs.
  arXiv  Detail & Related papers  (2024-08-09T20:55:46Z)
• Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model [51.83436609094658]
  We introduce Coarse Correspondences, a simple lightweight method that enhances MLLMs' spatial-temporal reasoning with 2D images as input. Our method uses a lightweight tracking model to identify primary object correspondences between frames in a video or across different image viewpoints. We demonstrate that this simple training-free approach brings substantial gains to GPT4-V/O consistently on four benchmarks.
  arXiv  Detail & Related papers  (2024-08-01T17:57:12Z)
• 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)
• Tackling VQA with Pretrained Foundation Models without Further Training [0.0]
  Large language models (LLMs) have achieved state-of-the-art results in many natural language processing tasks. With the capability of these LLMs, researchers have looked into how to adopt them for use with Visual Question Answering (VQA) In this paper, we explore a method of combining pretrained LLMs and other foundation models without further training to solve the VQA problem.
  arXiv  Detail & Related papers  (2023-09-27T08:35:24Z)
• Modular Visual Question Answering via Code Generation [134.59005611826777]
  We present a framework that formulates visual question answering as modular code generation. Our approach requires no additional training and relies on pre-trained language models (LMs), visual models pre-trained on image-caption pairs, and fifty VQA examples used for in-context learning. Our approach improves accuracy on the COVR dataset by at least 3% and on the GQA dataset by roughly 2% compared to the few-shot baseline that does not employ code generation.
  arXiv  Detail & Related papers  (2023-06-08T17:45:14Z)
• From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models [111.42052290293965]
  Large language models (LLMs) have demonstrated excellent zero-shot generalization to new language tasks. End-to-end training on vision and language data may bridge the disconnections, but is inflexible and computationally expensive. We propose emphImg2Prompt, a plug-and-play module that provides the prompts that can bridge the aforementioned modality and task disconnections.
  arXiv  Detail & Related papers  (2022-12-21T08:39:36Z)

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.