466 citations · 2.6k across the 60 of their papers we have counts for
15 papers · 1 filter
Causal Intervention for Weakly-Supervised Semantic Segmentation
Dong Zhang, Hanwang Zhang, Jinhui Tang +2
We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by using only im…
Interventional Few-Shot Learning
Zhongqi Yue, Hanwang Zhang, Qianru Sun +1
We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. This findi…
Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
Kaihua Tang, Jianqiang Huang, Hanwang Zhang
As the class size grows, maintaining a balanced dataset across many classes is challenging because the data are long-tailed in nature; it is even impossible when the sample-of-inte…
Ref-NMS: Breaking Proposal Bottlenecks in Two-Stage Referring Expression Grounding
Long Chen, Wenbo Ma, Jun Xiao +2
The prevailing framework for solving referring expression grounding is based on a two-stage process: 1) detecting proposals with an object detector and 2) grounding the referent to…
Feature Pyramid Transformer
Dong Zhang, Hanwang Zhang, Jinhui Tang +3
Feature interactions across space and scales underpin modern visual recognition systems because they introduce beneficial visual contexts. Conventionally, spatial contexts are pass…
Counterfactual VQA: A Cause-Effect Look at Language Bias
Yulei Niu, Kaihua Tang, Hanwang Zhang +3
VQA models may tend to rely on language bias as a shortcut and thus fail to sufficiently learn the multi-modal knowledge from both vision and language. Recent debiasing methods pro…
Iterative Context-Aware Graph Inference for Visual Dialog
Dan Guo, Hui Wang, Hanwang Zhang +2
Visual dialog is a challenging task that requires the comprehension of the semantic dependencies among implicit visual and textual contexts. This task can refer to the relation inf…
Learning to Segment the Tail
Xinting Hu, Yi Jiang, Kaihua Tang +3
Real-world visual recognition requires handling the extreme sample imbalance in large-scale long-tailed data. We propose a "divide&conquer" strategy for the challenging LVIS task:…
More Grounded Image Captioning by Distilling Image-Text Matching Model
Yuanen Zhou, Meng Wang, Daqing Liu +2
Visual attention not only improves the performance of image captioners, but also serves as a visual interpretation to qualitatively measure the caption rationality and model transp…
Counterfactual Samples Synthesizing for Robust Visual Question Answering
Long Chen, Xin Yan, Jun Xiao +3
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 trai…
Cross-GCN: Enhancing Graph Convolutional Network with -Order Feature Interactions
Fuli Feng, Xiangnan He, Hanwang Zhang +1
Graph Convolutional Network (GCN) is an emerging technique that performs learning and reasoning on graph data. It operates feature learning on the graph structure, through aggregat…
Deconfounded Image Captioning: A Causal Retrospect
Xu Yang, Hanwang Zhang, Jianfei Cai
Dataset bias in vision-language tasks is becoming one of the main problems which hinders the progress of our community. Existing solutions lack a principled analysis about why mode…
Visual Commonsense R-CNN
Tan Wang, Jianqiang Huang, Hanwang Zhang +1
We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual regi…
Unbiased Scene Graph Generation from Biased Training
Kaihua Tang, Yulei Niu, Jianqiang Huang +2
Today's scene graph generation (SGG) task is still far from practical, mainly due to the severe training bias, e.g., collapsing diverse "human walk on / sit on / lay on beach" into…
General Partial Label Learning via Dual Bipartite Graph Autoencoder
Brian Chen, Bo Wu, Alireza Zareian +2
We formulate a practical yet challenging problem: General Partial Label Learning (GPLL). Compared to the traditional Partial Label Learning (PLL) problem, GPLL relaxes the supervis…