Counterfactual Samples Synthesizing for Robust Visual Question Answering
Despite Visual Question Answering (VQA) has realized impressive progress over the last few years, today's VQA models tend to capture superficial linguistic correlations in the train set and fail to generalize to the test set with different QA distributions. To reduce the language biases, several recent works introduce an auxiliary question-only model to regularize the training of targeted VQA model, and achieve dominating performance on VQA-CP. However, since the complexity of design, current methods are unable to equip the ensemble-based models 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 question. To this end, we propose a model-agnostic Counterfactual Samples Synthesizing (CSS) training scheme. The CSS generates numerous counterfactual training samples by masking critical objects in images or words in questions, and assigning different ground-truth answers. After training with the complementary samples (ie, the original and generated samples), the VQA models are forced to focus on all critical objects and words, which significantly improves both visual-explainable and question-sensitive abilities. In return, the performance of these models is further boosted. Extensive ablations have shown the effectiveness of CSS. Particularly, by building on top of the model LMH, we achieve a record-breaking performance of 58.95% on VQA-CP v2, with 6.5% gains.
Code (2)
Tasks
counterfactualQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)Similar Papers 제목 키워드 기반
Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering
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 i…
counterfactualDiagnosticQuestion AnsweringVisual Question Answering+1Learning to Contrast the Counterfactual Samples for Robust Visual Question Answering
In the task of Visual Question Answering (VQA), most state-of-the-art models tend to learn spurious correlations in the training set and achieve poor performance in out-of-distribution test data. Some methods of generati…
Contrastive LearningcounterfactualDiagnosticQuestion Answering+2DMC$^3$: Dual-Modal Counterfactual Contrastive Construction for Egocentric Video Question Answering
Egocentric Video Question Answering (Egocentric VideoQA) plays an important role in egocentric video understanding, which refers to answering questions based on first-person videos. Although existing methods have made pr…
Video Question AnsweringSC-ML: Self-supervised Counterfactual Metric Learning for Debiased Visual Question Answering
Visual question answering (VQA) is a critical multimodal task in which an agent must answer questions according to the visual cue. Unfortunately, language bias is a common problem in VQA, which refers to the model genera…
counterfactualMetric LearningQuestion AnsweringVisual Question Answering+1Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models
Chart question-answering (QA) benchmarks aim to pose questions that require visual reasoning to correctly answer, but models can often reach solutions through shortcuts or prior familiarity with a chart based on their ow…
Visual Reasoning