Modular Visual Question Answering via Code Generation

• URL: http://arxiv.org/abs/2306.05392v1
• Date: Thu, 8 Jun 2023 17:45:14 GMT
• Title: Modular Visual Question Answering via Code Generation
• Authors: Sanjay Subramanian, Medhini Narasimhan, Kushal Khangaonkar, Kevin Yang, Arsha Nagrani, Cordelia Schmid, Andy Zeng, Trevor Darrell, Dan Klein
• Abstract summary: 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.
• Score: 134.59005611826777
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a framework that formulates visual question answering as modular code generation. In contrast to prior work on modular approaches to VQA, 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. The generated Python programs invoke and compose the outputs of the visual models using arithmetic and conditional logic. 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.

Related papers

• SparrowVQE: Visual Question Explanation for Course Content Understanding [12.926309478839652]
  This paper introduces Visual Question Explanation (VQE), which enhances the ability of VQA to provide detailed explanations. We trained our model with a three-stage training mechanism consisting of multimodal pre-training, instruction tuning, and domain fine-tuning. Experimental results demonstrate that our SparrowVQE achieves better performance in our developed MLVQE dataset and outperforms state-of-the-art methods in the other five benchmark VQA datasets.
  arXiv  Detail & Related papers  (2024-11-12T03:25:33Z)
• Pyramid Coder: Hierarchical Code Generator for Compositional Visual Question Answering [12.399738382728653]
  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.
  arXiv  Detail & Related papers  (2024-07-30T05:36:43Z)
• ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search [8.700556381819267]
  We introduce ProCQA, a large-scale programming question answering dataset extracted from the StackOverflow community. We propose a modality-agnostic contrastive pre-training approach to improve the alignment of text and code representations of current code language models.
  arXiv  Detail & Related papers  (2024-03-25T12:34:33Z)
• Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modeling [15.132926378740882]
  We propose a novel codebook transfer framework with part-of-speech, called VQCT, which aims to transfer a well-trained codebook from pretrained language models to VQIM. Experimental results on four datasets show that our VQCT method achieves superior VQIM performance over previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-03-15T07:24:13Z)
• VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models [58.21452697997078]
  We propose a novel VQAttack model, which can generate both image and text perturbations with the designed modules. Experimental results on two VQA datasets with five validated models demonstrate the effectiveness of the proposed VQAttack.
  arXiv  Detail & Related papers  (2024-02-16T21:17:42Z)
• Zero-shot Translation of Attention Patterns in VQA Models to Natural Language [65.94419474119162]
  ZS-A2T is a framework that translates the transformer attention of a given model into natural language without requiring any training. We consider this in the context of Visual Question Answering (VQA) Our framework does not require any training and allows the drop-in replacement of different guiding sources.
  arXiv  Detail & Related papers  (2023-11-08T22:18:53Z)
• 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)
• Zero-shot Visual Question Answering with Language Model Feedback [83.65140324876536]
  We propose a language model guided captioning approach, LAMOC, for knowledge-based visual question answering (VQA) Our approach employs the generated captions by a captioning model as the context of an answer prediction model, which is a Pre-trained Language model (PLM)
  arXiv  Detail & Related papers  (2023-05-26T15:04:20Z)
• CoSQA: 20,000+ Web Queries for Code Search and Question Answering [63.92224685262063]
  CoSQA dataset includes 20,604 labels for pairs of natural language queries and codes. We introduce a contrastive learning method dubbed CoCLR to enhance query-code matching. We show that evaluated on CodeXGLUE with the same CodeBERT model, training on CoSQA improves the accuracy of code question answering by 5.1%.
  arXiv  Detail & Related papers  (2021-05-27T15:37:21Z)
• Unsupervised Paraphrasing with Pretrained Language Models [85.03373221588707]
  We propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking. We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair and the ParaNMT datasets.
  arXiv  Detail & Related papers  (2020-10-24T11:55:28Z)

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.