Suppressing biased samples for robust VQA
Most existing visual question answering (VQA) models strongly rely on language bias to
answer questions, ie, they always tend to fit question-answer pairs on the train split and …
answer questions, ie, they always tend to fit question-answer pairs on the train split and …
Debiased Visual Question Answering via the perspective of question types
Abstract Visual Question Answering (VQA) aims to answer questions according to the given
image. However, current VQA models tend to rely solely on textual information from the …
image. However, current VQA models tend to rely solely on textual information from the …
Overcoming language priors for visual question answering via loss rebalancing label and global context
R Cao, Z Li - Uncertainty in Artificial Intelligence, 2023 - proceedings.mlr.press
Despite the advances in Visual Question Answering (VQA), many VQA models currently
suffer from language priors (ie generating answers directly from questions without using …
suffer from language priors (ie generating answers directly from questions without using …
Greedy gradient ensemble for robust visual question answering
Abstract Language bias is a critical issue in Visual Question Answering (VQA), where
models often exploit dataset biases for the final decision without considering the image …
models often exploit dataset biases for the final decision without considering the image …
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 …
Overcoming language priors via shuffling language bias for robust visual question answering
J Zhao, Z Yu, X Zhang, Y Yang - IEEE Access, 2023 - ieeexplore.ieee.org
Recent research has revealed the notorious language prior problem in visual question
answering (VQA) tasks based on visual-textual interaction, which indicates that well …
answering (VQA) tasks based on visual-textual interaction, which indicates that well …
Overcoming language priors with self-supervised learning for visual question answering
Most Visual Question Answering (VQA) models suffer from the language prior problem,
which is caused by inherent data biases. Specifically, VQA models tend to answer questions …
which is caused by inherent data biases. Specifically, VQA models tend to answer questions …
Towards robust visual question answering: Making the most of biased samples via contrastive learning
Models for Visual Question Answering (VQA) often rely on the spurious correlations, ie, the
language priors, that appear in the biased samples of training set, which make them brittle …
language priors, that appear in the biased samples of training set, which make them brittle …
Digging out discrimination information from generated samples for robust visual question answering
Abstract Visual Question Answering (VQA) aims to answer a textual question based on a
given image. Nevertheless, recent studies have shown that VQA models tend to capture the …
given image. Nevertheless, recent studies have shown that VQA models tend to capture the …
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 …