173 citations · 367 across the 39 of their papers we have counts for
15 papers · 1 filter
Deconfounded Visual Grounding
Jianqiang Huang, Yu Qin, Jiaxin Qi +2
We focus on the confounding bias between language and location in the visual grounding pipeline, where we find that the bias is the major visual reasoning bottleneck. For example,…
Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification
Beier Zhu, Yulei Niu, Xian-Sheng Hua +1
We address the overlooked unbiasedness in existing long-tailed classification methods: we find that their overall improvement is mostly attributed to the biased preference of tail…
How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?
Xinhsuai Dong, Luu Anh Tuan, Min Lin +2
The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks usi…
Introspective Distillation for Robust Question Answering
Yulei Niu, Hanwang Zhang
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 a…
Self-Supervised Learning Disentangled Group Representation as Feature
Tan Wang, Zhongqi Yue, Jianqiang Huang +2
A good visual representation is an inference map from observations (images) to features (vectors) that faithfully reflects the hidden modularized generative factors (semantics). In…
Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering
Long Chen, Yuhang Zheng, Yulei Niu +2
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 t…
Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completion
Yixin Cao, Xiang Ji, Xin Lv +3
We present InferWiki, a Knowledge Graph Completion (KGC) dataset that improves upon existing benchmarks in inferential ability, assumptions, and patterns. First, each testing sampl…
Auto-Parsing Network for Image Captioning and Visual Question Answering
Xu Yang, Chongyang Gao, Hanwang Zhang +1
We propose an Auto-Parsing Network (APN) to discover and exploit the input data's hidden tree structures for improving the effectiveness of the Transformer-based vision-language sy…
Causal Attention for Unbiased Visual Recognition
Tan Wang, Chang Zhou, Qianru Sun +1
Attention module does not always help deep models learn causal features that are robust in any confounding context, e.g., a foreground object feature is invariant to different back…
Transporting Causal Mechanisms for Unsupervised Domain Adaptation
Zhongqi Yue, Qianru Sun, Xian-Sheng Hua +1
Existing Unsupervised Domain Adaptation (UDA) literature adopts the covariate shift and conditional shift assumptions, which essentially encourage models to learn common features a…
Empowering Language Understanding with Counterfactual Reasoning
Fuli Feng, Jizhi Zhang, Xiangnan He +2
Present language understanding methods have demonstrated extraordinary ability of recognizing patterns in texts via machine learning. However, existing methods indiscriminately use…
Adversarial Visual Robustness by Causal Intervention
Kaihua Tang, Mingyuan Tao, Hanwang Zhang
Adversarial training is the de facto most promising defense against adversarial examples. Yet, its passive nature inevitably prevents it from being immune to unknown attackers. To…
VL-NMS: Breaking Proposal Bottlenecks in Two-Stage Visual-Language Matching
Chenchi Zhang, Wenbo Ma, Jun Xiao +4
The prevailing framework for matching multimodal inputs is based on a two-stage process: 1) detecting proposals with an object detector and 2) matching text queries with proposals.…
TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph
Jiaxin Shi, Shulin Cao, Lei Hou +2
Multi-hop Question Answering (QA) is a challenging task because it requires precise reasoning with entity relations at every step towards the answer. The relations can be represent…
The Blessings of Unlabeled Background in Untrimmed Videos
Yuan Liu, Jingyuan Chen, Zhenfang Chen +3
Weakly-supervised Temporal Action Localization (WTAL) aims to detect the action segments with only video-level action labels in training. The key challenge is how to distinguish th…