Adversarial regularization improves VQA performance on out-of-domain bias tests but introduces unstable gradients, reduced in-domain accuracy, and over-reliance on visual cues at the expense of linguistic information.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects
Adversarial regularization improves VQA performance on out-of-domain bias tests but introduces unstable gradients, reduced in-domain accuracy, and over-reliance on visual cues at the expense of linguistic information.