AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Overcoming Language Priors in Visual Question Answering with Adversarial Regularization

Sainandan Ramakrishnan, Aishwarya Agrawal, Stefan Lee

NeurIPS 2018 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 17 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add question-only adversarial regularization (ablation)SAN · VQA-CP v2 testoverall accuracy: 24.96 -> 27.24Improved
Add difference-of-entropies regularization (ablation)SAN · VQA-CP v2 testoverall accuracy: 24.96 -> 25.75Improved
Add both Q-Adv and DoE regularizers (ablation)SAN · VQA-CP v2 testoverall accuracy: 24.96 -> 33.29Improved
Add question-only adversarial regularization (ablation)UpDn · VQA-CP v2 testoverall accuracy: 39.74 -> 40.08Improved
Add difference-of-entropies regularization (ablation)UpDn · VQA-CP v2 testoverall accuracy: 39.74 -> 40.43Improved
Add both Q-Adv and DoE regularizers (ablation)UpDn · VQA-CP v2 testoverall accuracy: 39.74 -> 41.17Improved
Add both Q-Adv and DoE regularizers (ablation)SAN · VQA-CP v1 testoverall accuracy: 26.88 -> 43.43Improved
Add both Q-Adv and DoE regularizers (ablation)SAN · VQA v2 valoverall accuracy: 52.41 -> 52.31No clear effect
Add both Q-Adv and DoE regularizers (ablation)UpDn · VQA v2 valoverall accuracy: 63.48 -> 62.75Hurt
Add both Q-Adv and DoE regularizers (ablation)SAN · VQA v1 valoverall accuracy: 55.86 -> 52.15Hurt
Add Q-Adv and DoE to the question encoder (ablation)SAN question-only model · VQA-CP v2 trainoverall accuracy: 24.83 -> 13.84Hurt
Use DoE alongside Q-Adv while sweeping the Q-Adv coefficient (ablation)SAN · VQA-CP v2 testoverall accuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy