1 code implementation • 6 Aug 2022 • Jiaxin Qi, Kaihua Tang, Qianru Sun, Xian-Sheng Hua, Hanwang Zhang
If the context in every class is evenly distributed, OOD would be trivial because the context can be easily removed due to an underlying principle: class is invariant to context.
1 code implementation • 19 Jul 2022 • Kaihua Tang, Mingyuan Tao, Jiaxin Qi, Zhenguang Liu, Hanwang Zhang
In fact, even if the class is balanced, samples within each class may still be long-tailed due to the varying attributes.
Ranked #1 on Long-tail Learning on ImageNet-GLT
no code implementations • 31 Dec 2021 • Jianqiang Huang, Yu Qin, Jiaxin Qi, Qianru Sun, Hanwang Zhang
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.
1 code implementation • CVPR 2020 • Jiaxin Qi, Yulei Niu, Jianqiang Huang, Hanwang Zhang
This paper unravels the design tricks adopted by us, the champion team MReaL-BDAI, for Visual Dialog Challenge 2019: two causal principles for improving Visual Dialog (VisDial).