VALSE 首页 活动通知 好文作者面授招 查看内容

20170510-09 魏云超:Weakly-supervised semantic segmentation with...

2017-5-9 11:46| 发布者: 程一-计算所| 查看: 6321| 评论: 0

摘要: 报告嘉宾2:魏云超(National University of Singapore)报告时间:2017年05月10日(星期三)晚21:00(北京时间)报告题目:Weakly-supervised semantic segmentation with Image-level Annotation主持人:何晖光( ...

报告嘉宾2:魏云超(National University of Singapore)
报告题目:Weakly-supervised semantic segmentation with Image-level Annotation

Among various levels of supervision information (e.g. labels, bounding boxes and pixel-level annotations), the simplest and most efficient one that can be collected for training is the image-level object category annotation. In this talk, he will introduce his recent efforts on weakly-supervised semantic segmentation. His works achieve some state-of-the-art results on these challenging tasks. 

[1] Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach. Yunchao Wei, Jiashi Feng, Xiaodan Liang, Ming-Ming Cheng, Yao Zhao, Shuicheng Yan. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 (oral)
[2] STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation. Yunchao Wei, Xiaodan Liang, Yunpeng Chen, Xiaohui Shen, Ming-Ming Cheng, Jiashi Feng, Yao Zhao, Shuicheng Yan. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017
[3] Learning to segment with image-level annotations. Yunchao Wei, Xiaodan Liang, Yunpeng Chen, Zequn Jie, Yanhui Xiao, Yao Zhao, Shuicheng Yan. Pattern Recognition (PR), 2016

Yunchao Wei is currently a research fellow in Learning and Vision Research Group at the Department of Electrical and Computer Engineering, National University of Singapore, directed by Prof. Jiashi Feng and Prof. Shuicheng Yan. He received his PhD degree from Beijing Jiaotong University in 2016 under guidance of Prof. Yao Zhao.  His research primarily centers on image understanding and deep learning, including multi-modal analysis, image classification, object detection and semantic segmentation. He has published several papers on prestigious international journals and top conference, such as TPAMI, CVPR, ICCV and so on. He received the Winner Prize of Object Detection Task (1a) in ILSVRC-2014, Excellent Doctoral Dissertation Award of CIE in 2016.

VODB协调理事:禹之鼎(Carnegie Mellon University),程明明(南开大学)


小黑屋|手机版|Archiver|Vision And Learning SEminar

GMT+8, 2021-4-14 06:58 , Processed in 0.012830 second(s), 15 queries .

Powered by Discuz! X3.4

Copyright © 2001-2020, Tencent Cloud.