no code implementations • 11 Dec 2022 • Yiqi Lin, Huabin Zheng, Huaping Zhong, Jinjing Zhu, Weijia Li, Conghui He, Lin Wang
To address these issues, we build a task-specific self-supervised pre-training framework from a data selection perspective based on a simple hypothesis that pre-training on the unlabeled samples with similar distribution to the target task can bring substantial performance gains.
2 code implementations • ICCV 2021 • Jingkang Yang, Haoqi Wang, Litong Feng, Xiaopeng Yan, Huabin Zheng, Wayne Zhang, Ziwei Liu
The proposed UDG can not only enrich the semantic knowledge of the model by exploiting unlabeled data in an unsupervised manner, but also distinguish ID/OOD samples to enhance ID classification and OOD detection tasks simultaneously.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 13 Aug 2021 • Xiaopeng Yan, Riquan Chen, Litong Feng, Jingkang Yang, Huabin Zheng, Wayne Zhang
In this paper, we propose to label only the most representative samples to expand the labeled set.
1 code implementation • 12 Oct 2020 • Jingkang Yang, Weirong Chen, Litong Feng, Xiaopeng Yan, Huabin Zheng, Wayne Zhang
VSGraph-LC starts from anchor selection referring to the semantic similarity between metadata and correct label concepts, and then propagates correct labels from anchors on a visual graph using graph neural network (GNN).
Ranked #9 on Image Classification on WebVision-1000
4 code implementations • ECCV 2020 • Jingkang Yang, Litong Feng, Weirong Chen, Xiaopeng Yan, Huabin Zheng, Ping Luo, Wayne Zhang
Therefore, a simple yet effective WSL framework is proposed.
Ranked #7 on Image Classification on WebVision-1000
5 code implementations • ECCV 2018 • Bochao Wang, Huabin Zheng, Xiaodan Liang, Yimin Chen, Liang Lin, Meng Yang
Second, to alleviate boundary artifacts of warped clothes and make the results more realistic, we employ a Try-On Module that learns a composition mask to integrate the warped clothes and the rendered image to ensure smoothness.
no code implementations • 7 Nov 2016 • Huabin Zheng, Jingyu Wang, Zhengjie Huang, Yang Yang, Rong pan
We take advantage of the successful architecture called fully convolutional networks (FCN) in the field of semantic segmentation.