Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering

• URL: http://arxiv.org/abs/2404.12020v3
• Date: Mon, 21 Oct 2024 07:23:37 GMT
• Title: Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering
• Authors: Jie Ma, Min Hu, Pinghui Wang, Wangchun Sun, Lingyun Song, Hongbin Pei, Jun Liu, Youtian Du,
• Abstract summary: We propose a novel dataset, MUSIC-AVQA-R, crafted in two steps: rephrasing questions within the test split of a public dataset (MUSIC-AVQA) and introducing distribution shifts to split questions. Experimental results show that this architecture achieves state-of-the-art performance on MUSIC-AVQA-R, notably obtaining a significant improvement of 9.32%.
• Score: 25.577314828249897
• License:
• Abstract: Audio-Visual Question Answering (AVQA) is a complex multi-modal reasoning task, demanding intelligent systems to accurately respond to natural language queries based on audio-video input pairs. Nevertheless, prevalent AVQA approaches are prone to overlearning dataset biases, resulting in poor robustness. Furthermore, current datasets may not provide a precise diagnostic for these methods. To tackle these challenges, firstly, we propose a novel dataset, MUSIC-AVQA-R, crafted in two steps: rephrasing questions within the test split of a public dataset (MUSIC-AVQA) and subsequently introducing distribution shifts to split questions. The former leads to a large, diverse test space, while the latter results in a comprehensive robustness evaluation on rare, frequent, and overall questions. Secondly, we propose a robust architecture that utilizes a multifaceted cycle collaborative debiasing strategy to overcome bias learning. Experimental results show that this architecture achieves state-of-the-art performance on MUSIC-AVQA-R, notably obtaining a significant improvement of 9.32%. Extensive ablation experiments are conducted on the two datasets mentioned to analyze the component effectiveness within the debiasing strategy. Additionally, we highlight the limited robustness of existing multi-modal QA methods through the evaluation on our dataset. We also conduct experiments combining various baselines with our proposed strategy on two datasets to verify its plug-and-play capability. Our dataset and code are available at https://github.com/reml-group/MUSIC-AVQA-R.

Related papers

• Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent [102.31558123570437]
  Multimodal Retrieval Augmented Generation (mRAG) plays an important role in mitigating the "hallucination" issue inherent in multimodal large language models (MLLMs) We propose the first self-adaptive planning agent for multimodal retrieval, OmniSearch.
  arXiv  Detail & Related papers  (2024-11-05T09:27:21Z)
• UNK-VQA: A Dataset and a Probe into the Abstention Ability of Multi-modal Large Models [55.22048505787125]
  This paper contributes a comprehensive dataset, called UNK-VQA. We first augment the existing data via deliberate perturbations on either the image or question. We then extensively evaluate the zero- and few-shot performance of several emerging multi-modal large models.
  arXiv  Detail & Related papers  (2023-10-17T02:38:09Z)
• Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering [10.00386025149584]
  We review each question type from the original dataset, selecting those with pronounced answer biases. We gather complementary videos and questions, ensuring that no answers have outstanding skewed distribution. We present a novel baseline model that delves deeper into the audio-visual-text interrelation.
  arXiv  Detail & Related papers  (2023-10-10T01:22:41Z)
• Read, Look or Listen? What's Needed for Solving a Multimodal Dataset [7.0430001782867]
  We propose a two-step method to analyze multimodal datasets, which leverages a small seed of human annotation to map each multimodal instance to the modalities required to process it. We apply our approach to TVQA, a video question-answering dataset, and discover that most questions can be answered using a single modality, without a substantial bias towards any specific modality. We analyze the MERLOT Reserve, finding that it struggles with image-based questions compared to text and audio, but also with auditory speaker identification.
  arXiv  Detail & Related papers  (2023-07-06T08:02:45Z)
• Modern Question Answering Datasets and Benchmarks: A Survey [5.026863544662493]
  Question Answering (QA) is one of the most important natural language processing (NLP) tasks. It aims using NLP technologies to generate a corresponding answer to a given question based on the massive unstructured corpus. In this paper, we investigate influential QA datasets that have been released in the era of deep learning.
  arXiv  Detail & Related papers  (2022-06-30T05:53:56Z)
• Learning to Answer Questions in Dynamic Audio-Visual Scenarios [81.19017026999218]
  We focus on the Audio-Visual Questioning (AVQA) task, which aims to answer questions regarding different visual objects sounds, and their associations in videos. Our dataset contains more than 45K question-answer pairs spanning over different modalities and question types. Our results demonstrate that AVQA benefits from multisensory perception and our model outperforms recent A-SIC, V-SIC, and AVQA approaches.
  arXiv  Detail & Related papers  (2022-03-26T13:03:42Z)
• MGA-VQA: Multi-Granularity Alignment for Visual Question Answering [75.55108621064726]
  Learning to answer visual questions is a challenging task since the multi-modal inputs are within two feature spaces. We propose Multi-Granularity Alignment architecture for Visual Question Answering task (MGA-VQA) Our model splits alignment into different levels to achieve learning better correlations without needing additional data and annotations.
  arXiv  Detail & Related papers  (2022-01-25T22:30:54Z)
• Beyond Accuracy: A Consolidated Tool for Visual Question Answering Benchmarking [30.155625852894797]
  We propose a browser-based benchmarking tool for researchers and challenge organizers. Our tool helps test generalization capabilities of models across multiple datasets. Interactive filtering facilitates discovery of problematic behavior.
  arXiv  Detail & Related papers  (2021-10-11T11:08:35Z)
• Learning with Instance Bundles for Reading Comprehension [61.823444215188296]
  We introduce new supervision techniques that compare question-answer scores across multiple related instances. Specifically, we normalize these scores across various neighborhoods of closely contrasting questions and/or answers. We empirically demonstrate the effectiveness of training with instance bundles on two datasets.
  arXiv  Detail & Related papers  (2021-04-18T06:17:54Z)
• Improving Multi-Turn Response Selection Models with Complementary Last-Utterance Selection by Instance Weighting [84.9716460244444]
  We consider utilizing the underlying correlation in the data resource itself to derive different kinds of supervision signals. We conduct extensive experiments in two public datasets and obtain significant improvement in both datasets.
  arXiv  Detail & Related papers  (2020-02-18T06:29:01Z)

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.