2023-07-02-cao23a.md

abstract	openreview	title	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Despite the advances in Visual Question Answering (VQA), many VQA models currently suffer from language priors (i.e. generating answers directly from questions without using images), which severely reduces their robustness in real-world scenarios. We propose a novel training strategy called Loss Rebalancing Label and Global Context (LRLGC) to alleviate the above problem. Specifically, the Loss Rebalancing Label (LRL) is dynamically constructed based on the degree of sample bias to accurately adjust losses across samples and ensure a more balanced form of total losses in VQA. In addition, the Global Context (GC) provides the model with valid global information to assist the model in predicting answers more accurately. Finally, the model is trained through an ensemble-based approach that retains the beneficial effects of biased samples on the model while reducing their importance. Our approach is model-agnostic and enables end-to-end training. Extensive experimental results show that LRLGC (1) improves performance for various VQA models and (2) performs competitively in the VQA-CP v2 benchmark test.	FEDih5lICO	Overcoming Language Priors for Visual Question Answering via Loss Rebalancing Label and Global Context	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	cao23a	0	Overcoming Language Priors for Visual Question Answering via Loss Rebalancing Label and Global Context	249	259	249-259	249	false	Cao, Runlin and Li, Zhixin	given family Runlin Cao given family Zhixin Li	2023-07-02		Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence	216	inproceedings	date-parts 2023 7 2	https://proceedings.mlr.press/v216/cao23a/cao23a.pdf