Quantifying and alleviating the language prior problem in visual question answering
Benefiting from the advancement of computer vision, natural language processing and
information retrieval techniques, visual question answering (VQA), which aims to answer …
information retrieval techniques, visual question answering (VQA), which aims to answer …
Regulating Balance Degree for More Reasonable Visual Question Answering Benchmark
K Lin, A Mao, J Liu - 2022 International Joint Conference on …, 2022 - ieeexplore.ieee.org
Superficial linguistic correlations is a critical issue for Visual Question Answering (VQA),
where models can achieve high performance by exploiting the connection between question …
where models can achieve high performance by exploiting the connection between question …
Loss re-scaling VQA: Revisiting the language prior problem from a class-imbalance view
Recent studies have pointed out that many well-developed Visual Question Answering
(VQA) models are heavily affected by the language prior problem. It refers to making …
(VQA) models are heavily affected by the language prior problem. It refers to making …
Vqa-bc: Robust visual question answering via bidirectional chaining
Current VQA models are suffering from the problem of overdependence on language bias,
which severely reduces their robustness in real-world scenarios. In this paper, we analyze …
which severely reduces their robustness in real-world scenarios. In this paper, we analyze …
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 …
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 …
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 …
Simple contrastive learning in a self-supervised manner for robust visual question answering
Recent observations have revealed that Visual Question Answering models are susceptible
to learning the spurious correlations formed by dataset biases, ie, the language priors …
to learning the spurious correlations formed by dataset biases, ie, the language priors …
A Multi-modal Debiasing Model with Dynamical Constraint for Robust Visual Question Answering
Recent studies have pointed out that many well-developed Visual Question Answering
(VQA) systems suffer from bias problem. Despite the remarkable performance gained on In …
(VQA) systems suffer from bias problem. Despite the remarkable performance gained on In …
Fair Attention Network for Robust Visual Question Answering
As a prevailing cross-modal reasoning task, Visual Question Answering (VQA) has achieved
impressive progress in the last few years, where the language bias is widely studied to learn …
impressive progress in the last few years, where the language bias is widely studied to learn …