Contrast and Classify: Training Robust VQA Models
Yash Kant1
Abhinav Moudgil1
Dhruv Batra1,2
Devi Parikh1,2
Harsh Agrawal1
1Georgia Tech
2Facebook AI Research
Published at ICCV, 2021
Overview of ConCAT. (a) We augment the VQA dataset by paraphrasing every question via back-translation. (b) We carefully curate a contrastive batch by sampling different types of positives and negatives to learn joint V+L representations by minimizing scaled supervised contrastive loss. (c) Cross Entropy iteration.


Recent Visual Question Answering (VQA) models have shown impressive performance on the VQA benchmark but remain sensitive to small linguistic variations in input questions. Existing approaches address this by augmenting the dataset with question paraphrases from visual question generation models or adversarial perturbations. These approaches use the combined data to learn an answer classifier by minimizing the standard cross-entropy loss. To more effectively leverage augmented data, we build on the recent success in contrastive learning. We propose a novel training paradigm (ConClaT) that optimizes both cross-entropy and contrastive losses. The contrastive loss encourages representations to be robust to linguistic variations in questions while the cross-entropy loss preserves the discriminative power of representations for answer prediction. We find that optimizing both losses -- either alternately or jointly -- is key to effective training. On the VQA-Rephrasings benchmark, which measures the VQA model's answer consistency across human paraphrases of a question, ConClaT improves Consensus Score by 1 .63% over an improved baseline. In addition, on the standard VQA 2.0 benchmark, we improve the VQA accuracy by 0.78% overall. We also show that ConClaT is agnostic to the type of data-augmentation strategy used.

Paper and Bibtex

Kant, Y., Moudgil, A., Batra, D., Parikh, D., & Agrawal, H. 2020. Contrast and Classify: Training Robust VQA Models . ICCV.

  title={Contrast and Classify: Training Robust VQA Models},
  author={Yash Kant and Abhinav Moudgil and Dhruv Batra  
          and Devi Parikh and Harsh Agrawal},



We thank Abhishek Das, Prithvijit Chattopadhyay and Arjun Majumdar for their feedback. The Georgia Tech effort was supported in part by NSF, AFRL, DARPA, ONR YIPs, ARO PECASE, Amazon. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the U.S. Government, or any sponsor.

This template was originally made by Phillip Isola and Richard Zhang for a colorful ECCV project; the code can be found here.