paper-with-me

Papers

Counterfactual Samples Synthesizing for Robust Visual Question Answering

2020-03-14 · CVPR 2020 6 · Long Chen, Xin Yan, Jun Xiao, Hanwang Zhang, ShiLiang Pu, Yueting Zhuang

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.

📄 PDF Abstract BibTeX arXiv:2003.06576

Code (2)

yanxinzju/CSS-VQA 공식 구현 pytorch
FengSuSky/CCB-VQA pytorch

Tasks

counterfactualQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering

2021-10-03 · Long Chen, Yuhang Zheng, Yulei Niu, Hanwang Zhang 외

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+1

Learning to Contrast the Counterfactual Samples for Robust Visual Question Answering

2020-11-01 · EMNLP 2020 11 · Zujie Liang, Weitao Jiang, Haifeng Hu, Jiaying Zhu

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+2

DMC$^3$: Dual-Modal Counterfactual Contrastive Construction for Egocentric Video Question Answering

2025-10-23 · Jiayi Zou, Chaofan Chen, Bing-Kun Bao, Changsheng Xu arxiv

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 Answering

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

2023-04-04 · Xinyao Shu, ShiYang Yan, Xu Yang, Ziheng Wu 외

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+1

Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models

2026-05-26 · Yifan Jiang, Dae Yon Hwang, Jesse C. Cresswell, Freda Shi arxiv

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