Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded

International Conference on Computer Vision (ICCV)


Many vision and language models suffer from poor visual grounding – often falling back on easy-to-learn language priors rather than basing their decisions on visual concepts in the image. In this work, we propose a generic approach called Human Importance-aware Network Tuning (HINT) that effectively leverages human demonstrations to improve visual grounding. HINT encourages deep networks to be sensitive to the same input regions as humans. Our approach optimizes the alignment between human attention maps and gradient-based network importances – ensuring that models learn not just to look at but rather rely on visual concepts that humans found relevant for a task when making predictions. We apply HINT to Visual Question Answering and Image Captioning tasks, outperforming top approaches on splits that penalize over-reliance on language priors (VQA-CP and robust captioning) using human attention demonstrations for just 6% of the training data.

Related Publications

All Publications

MICCAI - October 5, 2020

Active MR k-space Sampling with Reinforcement Learning

Luis Pineda, Sumana Basu, Adriana Romero, Roberto Calandra, Michal Drozdzal

Multimodal Video Analysis Workshop at ECCV - August 23, 2020

Audio-Visual Instance Discrimination

Pedro Morgado, Nuno Vasconcelos, Ishan Misra

Interspeech - October 24, 2020

Efficient Wait-k Models for Simultaneous Machine Translation

Maha Elbayad, Laurent Besacier, Jakob Verbeek

ICML - November 3, 2020

Learning Near Optimal Policies with Low Inherent Bellman Error

Andrea Zanette, Alessandro Lazaric, Mykel J. Kochenderfer, Emma Brunskill

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy