Filters








3 Hits in 5.1 sec

Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation [article]

Weifeng Ge, Sheng Guo, Weilin Huang, Matthew R. Scott
2020 arXiv   pre-print
Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only.  ...  Unlike previous methods which are composed of multiple offline stages, we propose Sequential Label Propagation and Enhancement Networks (referred as Label-PEnet) that progressively transform image-level  ...  Conclusions We have presented new Sequential Label Propagation and Enhancement Networks (referred as Label-PEnet) for weakly-supervised object detection and instance segmentation.  ... 
arXiv:1910.02624v3 fatcat:c5w76g7ikrc6jgp5kzgpuh4lcu

Weakly Supervised Instance Segmentation by Deep Community Learning [article]

Jaedong Hwang, Seohyun Kim, Jeany Son, Bohyung Han
2020 arXiv   pre-print
We present a weakly supervised instance segmentation algorithm based on deep community learning with multiple tasks.  ...  This task is formulated as a combination of weakly supervised object detection and semantic segmentation, where individual objects of the same class are identified and segmented separately.  ...  Figure 2 . 2 The proposed network architecture for weakly supervised instance segmentation.  ... 
arXiv:2001.11207v3 fatcat:b5wdslbtezf65ezansgzdkisai

Table of Contents

2019 2019 IEEE/CVF International Conference on Computer Vision (ICCV)  
Enhancement Networks for Weakly Supervised Instance Segmentation 3344 Weifeng Ge (The University of Hong Kong), Weilin Huang (Malong Technologies), Sheng Guo (Malong Technologies), and Matthew Scott (  ...  Seoul National University), Seokil Hong (Seoul National University), Bohyung Han (Seoul National University), and Kyoung Mu Lee (Seoul National University) Label-PEnet: Sequential Label Propagation and  ... 
doi:10.1109/iccv.2019.00004 fatcat:5aouo4scprc75c7zetsimylj2y