Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Xiaolin Wei

Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning


Aug 12, 2021
Junkai Huang, Chaowei Fang, Weikai Chen, Zhenhua Chai, Xiaolin Wei, Pengxu Wei, Liang Lin, Guanbin Li

* Accepted by ICCV2021 

  Access Paper or Ask Questions

Structure Guided Lane Detection


May 12, 2021
Jinming Su, Chao Chen, Ke Zhang, Junfeng Luo, Xiaoming Wei, Xiaolin Wei

* Accepted by IJCAI 2021 

  Access Paper or Ask Questions

Twins: Revisiting the Design of Spatial Attention in Vision Transformers


May 11, 2021
Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren, Xiaolin Wei, Huaxia Xia, Chunhua Shen

* Two simple and effective designs of vision transformer, which is on par with the Swin transformer 

  Access Paper or Ask Questions

Twins: Revisiting Spatial Attention Design in Vision Transformers


Apr 28, 2021
Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren, Xiaolin Wei, Huaxia Xia, Chunhua Shen

* Two simple and effective designs of vision transformer, which is on par with the Swin transformer 

  Access Paper or Ask Questions

Rethinking BiSeNet For Real-time Semantic Segmentation


Apr 27, 2021
Mingyuan Fan, Shenqi Lai, Junshi Huang, Xiaoming Wei, Zhenhua Chai, Junfeng Luo, Xiaolin Wei


  Access Paper or Ask Questions

Large Scale Visual Food Recognition


Mar 31, 2021
Weiqing Min, Zhiling Wang, Yuxin Liu, Mengjiang Luo, Liping Kang, Xiaoming Wei, Xiaolin Wei, Shuqiang Jiang


  Access Paper or Ask Questions

Conditional Positional Encodings for Vision Transformers


Mar 18, 2021
Xiangxiang Chu, Zhi Tian, Bo Zhang, Xinlong Wang, Xiaolin Wei, Huaxia Xia, Chunhua Shen

* A general purpose conditional position encoding for vision transformers 

  Access Paper or Ask Questions

Do We Really Need Explicit Position Encodings for Vision Transformers?


Feb 22, 2021
Xiangxiang Chu, Bo Zhang, Zhi Tian, Xiaolin Wei, Huaxia Xia

* A general purpose conditional position encoding for visual transformer 

  Access Paper or Ask Questions

Scene Text Detection with Scribble Lines


Dec 10, 2020
Wenqing Zhang, Yang Qiu, Minghui Liao, Rui Zhang, Xiaolin Wei, Xiang Bai


  Access Paper or Ask Questions

Beyond Single Instance Multi-view Unsupervised Representation Learning


Nov 26, 2020
Xiangxiang Chu, Xiaohang Zhan, Xiaolin Wei

* A plug-in approach with minimal modification to existing methods based on instance discrimination 

  Access Paper or Ask Questions

ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradients Accumulation


Nov 23, 2020
Xiaoxing Wang, Xiangxiang Chu, Yuda Fan, Zhexi Zhang, Xiaolin Wei, Junchi Yan, Xiaokang Yang

* Observe new collapse in memory efficient NAS and address it using ROME 

  Access Paper or Ask Questions

Free-Form Image Inpainting via Contrastive Attention Network


Oct 29, 2020
Xin Ma, Xiaoqiang Zhou, Huaibo Huang, Zhenhua Chai, Xiaolin Wei, Ran He

* Accepted by ICPR 2020 

  Access Paper or Ask Questions

DARTS-: Robustly Stepping out of Performance Collapse Without Indicators


Sep 02, 2020
Xiangxiang Chu, Xiaoxing Wang, Bo Zhang, Shun Lu, Xiaolin Wei, Junchi Yan

* A very robust, efficient and indicator-free approach to address the collapse of differentiable architecture search. Point out some issues of indicator based methods 

  Access Paper or Ask Questions

Query Twice: Dual Mixture Attention Meta Learning for Video Summarization


Aug 19, 2020
Junyan Wang, Yang Bai, Yang Long, Bingzhang Hu, Zhenhua Chai, Yu Guan, Xiaolin Wei

* This manuscript has been accepted at ACM MM 2020 

  Access Paper or Ask Questions

ISIA Food-500: A Dataset for Large-Scale Food Recognition via Stacked Global-Local Attention Network


Aug 13, 2020
Weiqing Min, Linhu Liu, Zhiling Wang, Zhengdong Luo, Xiaoming Wei, Xiaolin Wei, Shuqiang Jiang

* Accepted by ACM Multimedia 2020 

  Access Paper or Ask Questions

FedOCR: Communication-Efficient Federated Learning for Scene Text Recognition


Jul 22, 2020
Wenqing Zhang, Yang Qiu, Song Bai, Rui Zhang, Xiaolin Wei, Xiang Bai


  Access Paper or Ask Questions

ReADS: A Rectified Attentional Double Supervised Network for Scene Text Recognition


Apr 07, 2020
Qi Song, Qianyi Jiang, Nan Li, Rui Zhang, Xiaolin Wei

* 8 pages, 3 figures 

  Access Paper or Ask Questions