Roses are red, violets are blue... but should vqa expect them to?
C Kervadec, G Antipov… - Proceedings of the …, 2021 - openaccess.thecvf.com
Abstract Models for Visual Question Answering (VQA) are notorious for their tendency to rely
on dataset biases, as the large and unbalanced diversity of questions and concepts involved …
on dataset biases, as the large and unbalanced diversity of questions and concepts involved …
Unbiased Visual Question Answering by Leveraging Instrumental Variable
Y Pan, J Liu, L Jin, Z Li - IEEE Transactions on Multimedia, 2024 - ieeexplore.ieee.org
Existing unbiased visual question answering (VQA) models reduce the spurious correlation
between questions and answers to force the models to focus on visual information …
between questions and answers to force the models to focus on visual information …
A language prior based focal loss for visual question answering
According to current research, one of the major challenges in Visual Question Answering
(VQA) models is the overdependence on language priors (and neglect of the visual …
(VQA) models is the overdependence on language priors (and neglect of the visual …
Learning from lexical perturbations for consistent visual question answering
Existing Visual Question Answering (VQA) models are often fragile and sensitive to input
variations. In this paper, we propose a novel approach to address this issue based on …
variations. In this paper, we propose a novel approach to address this issue based on …
Counterfactual samples synthesizing for robust visual question answering
Abstract Despite Visual Question Answering (VQA) has realized impressive progress over
the last few years, today's VQA models tend to capture superficial linguistic correlations in …
the last few years, today's VQA models tend to capture superficial linguistic correlations in …
Debiased visual question answering from feature and sample perspectives
Visual question answering (VQA) is designed to examine the visual-textual reasoning ability
of an intelligent agent. However, recent observations show that many VQA models may only …
of an intelligent agent. However, recent observations show that many VQA models may only …
Robust visual question answering: Datasets, methods, and future challenges
J Ma, P Wang, D Kong, Z Wang, J Liu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Visual question answering requires a system to provide an accurate natural language
answer given an image and a natural language question. However, it is widely recognized …
answer given an image and a natural language question. However, it is widely recognized …
Swapmix: Diagnosing and regularizing the over-reliance on visual context in visual question answering
Abstract While Visual Question Answering (VQA) has progressed rapidly, previous works
raise concerns about robustness of current VQA models. In this work, we study the …
raise concerns about robustness of current VQA models. In this work, we study the …
Learning to contrast the counterfactual samples for robust visual question answering
In the task of Visual Question Answering (VQA), most state-of-the-art models tend to learn
spurious correlations in the training set and achieve poor performance in out-of-distribution …
spurious correlations in the training set and achieve poor performance in out-of-distribution …
Distilling knowledge in causal inference for unbiased visual question answering
Y Pan, Z Li, L Zhang, J Tang - Proceedings of the 2nd ACM International …, 2021 - dl.acm.org
Current Visual Question Answering (VQA) models mainly explore the statistical correlations
between answers and questions, which fail to capture the relationship between the visual …
between answers and questions, which fail to capture the relationship between the visual …