Timezone: »
Question answering (QA) models are well-known to exploit data bias, e.g., the language prior in visual QA and the position bias in reading comprehension. Recent debiasing methods achieve good out-of-distribution (OOD) generalizability with a considerable sacrifice of the in-distribution (ID) performance. Therefore, they are only applicable in domains where the test distribution is known in advance. In this paper, we present a novel debiasing method called Introspective Distillation (IntroD) to make the best of both worlds for QA. Our key technical contribution is to blend the inductive bias of OOD and ID by introspecting whether a training sample fits in the factual ID world or the counterfactual OOD one. Experiments on visual QA datasets VQA v2, VQA-CP, and reading comprehension dataset SQuAD demonstrate that our proposed IntroD maintains the competitive OOD performance compared to other debiasing methods, while sacrificing little or even achieving better ID performance compared to the non-debiasing ones.
Author Information
Yulei Niu (Nanyang Technological University)
Hanwang Zhang (NTU)
More from the Same Authors
-
2021 Spotlight: Self-Supervised Learning Disentangled Group Representation as Feature »
Tan Wang · Zhongqi Yue · Jianqiang Huang · Qianru Sun · Hanwang Zhang -
2022 Poster: Respecting Transfer Gap in Knowledge Distillation »
Yulei Niu · Long Chen · Chang Zhou · Hanwang Zhang -
2021 Poster: Self-Supervised Learning Disentangled Group Representation as Feature »
Tan Wang · Zhongqi Yue · Jianqiang Huang · Qianru Sun · Hanwang Zhang -
2021 Poster: How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness? »
Xinshuai Dong · Anh Tuan Luu · Min Lin · Shuicheng Yan · Hanwang Zhang -
2020 Poster: Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect »
Kaihua Tang · Jianqiang Huang · Hanwang Zhang -
2020 Poster: Causal Intervention for Weakly-Supervised Semantic Segmentation »
Dong Zhang · Hanwang Zhang · Jinhui Tang · Xian-Sheng Hua · Qianru Sun -
2020 Oral: Causal Intervention for Weakly-Supervised Semantic Segmentation »
Dong Zhang · Hanwang Zhang · Jinhui Tang · Xian-Sheng Hua · Qianru Sun -
2020 Poster: Interventional Few-Shot Learning »
Zhongqi Yue · Hanwang Zhang · Qianru Sun · Xian-Sheng Hua -
2018 Poster: Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks »
Hang Gao · Zheng Shou · Alireza Zareian · Hanwang Zhang · Shih-Fu Chang