AI Paper Atlas

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

Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning

David Mascharka, Philip Tran, Ryan Soklaski, Arjun Majumdar

CVPR 2018 · Vision-language and multimodal › Visual question answering · approach: Visual reasoning diagnostics · 206 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 attention-mask regularization (ablation)TbD-net · CLEVRoverall accuracy: 98.7 -> 98.5Hurt
Add attention-mask regularization (ablation)TbD-net · CLEVR attention interpretabilityrecall: 0.86 -> 0.92Improved
Add attention-mask regularization (ablation)TbD-net · CLEVR attention interpretabilityprecision: 0.41 -> 0.90Improved
Use 28×28 rather than 14×14 feature maps (ablation)TbD + reg · CLEVRoverall accuracy: 98.5 -> 99.1Improved
Use 28×28 rather than 14×14 feature maps (ablation)TbD + reg · CLEVR attention interpretabilityrecall: 0.92 -> 0.99Improved
Use 28×28 rather than 14×14 feature maps (ablation)TbD + reg · CLEVR attention interpretabilityprecision: 0.90 -> 0.98Improved
Train only on Condition A (ablation)TbD + reg · CLEVR-CoGenT Condition Baccuracy: 98.8 -> 75.4Hurt
Fine-tune on 3k Condition B images and 30k questions (ablation)TbD + reg · CLEVR-CoGenT Condition Baccuracy: 75.4 -> 96.3Improved
Fine-tune on 3k Condition B images and 30k questions (ablation)TbD + reg · CLEVR-CoGenT Condition Aaccuracy: 98.8 -> 96.9Mixed
Use TbD + reg + high-resolution feature maps instead of TbD-net (ablation)TbD-net · CLEVRoverall accuracy: 98.7 -> 99.1Improved

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