Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering

by   Long Chen, et al.

Today's VQA models still tend to capture superficial linguistic correlations in the training set and fail to generalize to the test set with different QA distributions. To reduce these language biases, recent VQA works introduce an auxiliary question-only model to regularize the training of targeted VQA model, and achieve dominating performance on diagnostic benchmarks for out-of-distribution testing. However, due to complex model design, these ensemble-based methods are unable to equip themselves with two indispensable characteristics of an ideal VQA model: 1) Visual-explainable: The model should rely on the right visual regions when making decisions. 2) Question-sensitive: The model should be sensitive to the linguistic variations in questions. To this end, we propose a novel model-agnostic Counterfactual Samples Synthesizing and Training (CSST) strategy. After training with CSST, VQA models are forced to focus on all critical objects and words, which significantly improves both visual-explainable and question-sensitive abilities. Specifically, CSST is composed of two parts: Counterfactual Samples Synthesizing (CSS) and Counterfactual Samples Training (CST). CSS generates counterfactual samples by carefully masking critical objects in images or words in questions and assigning pseudo ground-truth answers. CST not only trains the VQA models with both complementary samples to predict respective ground-truth answers, but also urges the VQA models to further distinguish the original samples and superficially similar counterfactual ones. To facilitate the CST training, we propose two variants of supervised contrastive loss for VQA, and design an effective positive and negative sample selection mechanism based on CSS. Extensive experiments have shown the effectiveness of CSST. Particularly, by building on top of model LMH+SAR, we achieve record-breaking performance on all OOD benchmarks.


page 1

page 2

page 5

page 11

page 12


Counterfactual Samples Synthesizing for Robust Visual Question Answering

Despite Visual Question Answering (VQA) has realized impressive progress...

Rethinking Data Augmentation for Robust Visual Question Answering

Data Augmentation (DA) – generating extra training samples beyond origin...

Revisiting Dense Retrieval with Unanswerable Counterfactuals

The retriever-reader framework is popular for open-domain question answe...

Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning

Models for Visual Question Answering (VQA) often rely on the spurious co...

Question-Conditioned Counterfactual Image Generation for VQA

While Visual Question Answering (VQA) models continue to push the state-...

Knowledge-Based Counterfactual Queries for Visual Question Answering

Visual Question Answering (VQA) has been a popular task that combines vi...

SC-ML: Self-supervised Counterfactual Metric Learning for Debiased Visual Question Answering

Visual question answering (VQA) is a critical multimodal task in which a...

Please sign up or login with your details

Forgot password? Click here to reset