Language Guided Visual Question Answering: Elevate Your Multimodal Language Model Using Knowledge-Enriched Prompts

• URL: http://arxiv.org/abs/2310.20159v1
• Date: Tue, 31 Oct 2023 03:54:11 GMT
• Title: Language Guided Visual Question Answering: Elevate Your Multimodal Language Model Using Knowledge-Enriched Prompts
• Authors: Deepanway Ghosal, Navonil Majumder, Roy Ka-Wei Lee, Rada Mihalcea, Soujanya Poria
• Abstract summary: Visual question answering (VQA) is the task of answering questions about an image. Answering the question requires commonsense knowledge, world knowledge, and reasoning about ideas and concepts not present in the image. We propose a framework that uses language guidance (LG) in the form of rationales, image captions, scene graphs, etc to answer questions more accurately.
• Score: 54.072432123447854
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Visual question answering (VQA) is the task of answering questions about an image. The task assumes an understanding of both the image and the question to provide a natural language answer. VQA has gained popularity in recent years due to its potential applications in a wide range of fields, including robotics, education, and healthcare. In this paper, we focus on knowledge-augmented VQA, where answering the question requires commonsense knowledge, world knowledge, and reasoning about ideas and concepts not present in the image. We propose a multimodal framework that uses language guidance (LG) in the form of rationales, image captions, scene graphs, etc to answer questions more accurately. We benchmark our method on the multi-choice question-answering task of the A-OKVQA, Science-QA, VSR, and IconQA datasets using CLIP and BLIP models. We show that the use of language guidance is a simple but powerful and effective strategy for visual question answering. Our language guidance improves the performance of CLIP by 7.6% and BLIP-2 by 4.8% in the challenging A-OKVQA dataset. We also observe consistent improvement in performance on the Science-QA, VSR, and IconQA datasets when using the proposed language guidances. The implementation of LG-VQA is publicly available at https:// github.com/declare-lab/LG-VQA.

Related papers

• Disentangling Knowledge-based and Visual Reasoning by Question Decomposition in KB-VQA [19.6585442152102]
  We study the Knowledge-Based visual question-answering problem, for which given a question, the models need to ground it into the visual modality to find the answer. Our study shows that replacing a complex question with several simpler questions helps to extract more relevant information from the image.
  arXiv  Detail & Related papers  (2024-06-27T02:19:38Z)
• Enhancing Visual Question Answering through Question-Driven Image Captions as Prompts [3.6064695344878093]
  Visual question answering (VQA) is known as an AI-complete task as it requires understanding, reasoning, and inferring about the vision and the language content. This study explores the impact of incorporating image captioning as an intermediary process within the VQA pipeline.
  arXiv  Detail & Related papers  (2024-04-12T16:35:23Z)
• OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamese [2.7528170226206443]
  We introduce the OpenViVQA dataset, the first large-scale dataset for visual question answering in Vietnamese. The dataset consists of 11,000+ images associated with 37,000+ question-answer pairs (QAs) Our proposed methods achieve results that are competitive with SOTA models such as SAAA, MCAN, LORA, and M4C.
  arXiv  Detail & Related papers  (2023-05-07T03:59:31Z)
• MaXM: Towards Multilingual Visual Question Answering [28.268881608141303]
  We propose scalable solutions to multilingual visual question answering (mVQA) on both data and modeling fronts. We first propose a translation-based framework to mVQA data generation that requires much less human annotation efforts than the conventional approach of directly collection questions and answers. Then, we apply our framework to the multilingual captions in the Crossmodal-3600 dataset and develop an efficient annotation protocol to create MaXM, a test-only VQA benchmark in 7 diverse languages.
  arXiv  Detail & Related papers  (2022-09-12T16:53:37Z)
• A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge [39.788346536244504]
  A-OKVQA is a crowdsourced dataset composed of about 25K questions. We demonstrate the potential of this new dataset through a detailed analysis of its contents.
  arXiv  Detail & Related papers  (2022-06-03T17:52:27Z)
• VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering [79.22069768972207]
  We propose VQA-GNN, a new VQA model that performs bidirectional fusion between unstructured and structured multimodal knowledge to obtain unified knowledge representations. Specifically, we inter-connect the scene graph and the concept graph through a super node that represents the QA context. On two challenging VQA tasks, our method outperforms strong baseline VQA methods by 3.2% on VCR and 4.6% on GQA, suggesting its strength in performing concept-level reasoning.
  arXiv  Detail & Related papers  (2022-05-23T17:55:34Z)
• K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition [64.55573343404572]
  We present a novel knowledge-aware VQG dataset called K-VQG. This is the first large, humanly annotated dataset in which questions regarding images are tied to structured knowledge. We also develop a new VQG model that can encode and use knowledge as the target for a question.
  arXiv  Detail & Related papers  (2022-03-15T13:38:10Z)
• An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA [51.639880603821446]
  We propose PICa, a simple yet effective method that Prompts GPT3 via the use of Image Captions for knowledge-based VQA. We first convert the image into captions (or tags) that GPT-3 can understand, then adapt GPT-3 to solve the VQA task in a few-shot manner. By using only 16 examples, PICa surpasses the supervised state of the art by an absolute +8.6 points on the OK-VQA dataset.
  arXiv  Detail & Related papers  (2021-09-10T17:51:06Z)
• Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding [140.5911760063681]
  We propose a novel dataset named Knowledge-Routed Visual Question Reasoning for VQA model evaluation. We generate the question-answer pair based on both the Visual Genome scene graph and an external knowledge base with controlled programs.
  arXiv  Detail & Related papers  (2020-12-14T00:33:44Z)
• CapWAP: Captioning with a Purpose [56.99405135645775]
  We propose a new task, Captioning with a Purpose (CapWAP) Our goal is to develop systems that can be tailored to be useful for the information needs of an intended population. We show that it is possible to use reinforcement learning to directly optimize for the intended information need.
  arXiv  Detail & Related papers  (2020-11-09T09:23:55Z)

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.