2023 · 54 citations · 33 references
ComputingComputer ScienceComputer VisionMachine LearningNatural Language ProcessingDeep LearningGenerative ModelingNeural NetworksQuestion AnsweringRepresentation LearningVisual Question AnsweringAdversarial Question AnsweringDataset BiasGenerative Adversarial NetworksKnowledge DistillationModel Bias
The task of Visual Question Answering (VQA) is known to be plagued by the issue of VQA models exploiting biases within the dataset to make its final prediction. Various previous ensemble based debiasing methods have been proposed where an additional model is purposefully trained to be biased in order to train a robust target model. However, these methods compute the bias for a model simply from the label statistics of the training data or from single modal branches. In this work, in order to better learn the bias a target VQA model suffers from, we propose a generative method to train the bias model directly from the target model, called GenB. In particular, GenB employs a generative network to learn the bias in the target model through a combination of the adversarial objective and knowledge distillation. We then debias our target model with GenB as a bias model, and show through extensive experiments the effects of our method on various VQA bias datasets including VQA-CP2, VQA-CP1, GQA-OOD, and VQA-CE, and show state-of-the-art results with the LXMERT architecture on VQA-CP2.
33
Distilling the Knowledge in a Neural Network
Geoffrey E. Hinton, Oriol Vinyals · arXiv (Cornell University) · 2015 · 14K citations · Full text
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Peter Anderson, Xiaodong He, Chris Buehler et al. · 2018 · 5.1K citations
VQA: Visual Question Answering
Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu et al. · 2015 · 4.3K citations
LXMERT: Learning Cross-Modality Encoder Representations from Transformers
Hao Tan, Mohit Bansal · 2019 · 2.3K citations · Full text