1 code implementation • 27 Mar 2023 • Chang Liu, Weiming Zhang, Xiangru Lin, Wei zhang, Xiao Tan, Junyu Han, Xiaomao Li, Errui Ding, Jingdong Wang
It employs a "divide-and-conquer" strategy and separately exploits positives for the classification and localization task, which is more robust to the assignment ambiguity.
no code implementations • 3 Jan 2023 • Haoyu Ma, Xiangru Lin, Yizhou Yu
This paper proposes a novel UDA pipeline for semantic segmentation that unifies image-level and feature-level adaptation.
no code implementations • CVPR 2021 • Xiangru Lin, Guanbin Li, Yizhou Yu
Intuitively, we comprehend the semantics of the instruction to form an overview of where a bathroom is and what a blue towel is in mind; then, we navigate to the target location by consistently matching the bathroom appearance in mind with the current scene.
no code implementations • CVPR 2021 • Haoyu Ma, Xiangru Lin, Zifeng Wu, Yizhou Yu
Unsupervised domain adaptation (UDA) in semantic segmentation is a fundamental yet promising task relieving the need for laborious annotation works.
Ranked #22 on Synthetic-to-Real Translation on SYNTHIA-to-Cityscapes
no code implementations • CVPR 2019 • Weifeng Ge, Xiangru Lin, Yizhou Yu
We build complementary parts models in a weakly supervised manner to retrieve information suppressed by dominant object parts detected by convolutional neural networks.
Ranked #20 on Fine-Grained Image Classification on CUB-200-2011