Weakly supervised segment annotation via expectation kernel density estimation
Since the labelling for the positive images/videos is ambiguous in weakly supervised segment annotation, negative mining‐based methods that only use the intra‐class information emerge. In these methods, negative instances are utilised to penalise unknown instances for ranking their likelihood of bei...
Main Authors: | Liantao Wang, Qingwu Li, Jianfeng Lu |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2019-06-01
|
Series: | IET Computer Vision |
Subjects: | |
Online Access: | https://doi.org/10.1049/iet-cvi.2018.5325 |
Similar Items
-
Non‐concept density estimation via kernel regression for concept ranking in weakly labelled data
by: Liantao Wang, et al.
Published: (2018-02-01) -
Attention-effective multiple instance learning on weakly stem cell colony segmentation
by: Novanto Yudistira, et al.
Published: (2023-02-01) -
Going to Extremes: Weakly Supervised Medical Image Segmentation
by: Holger R. Roth, et al.
Published: (2021-06-01) -
Weakly Supervised Instance Segmentation Based on Two-Stage Transfer Learning
by: Yongqing Sun, et al.
Published: (2020-01-01) -
Crop Organ Segmentation and Disease Identification Based on Weakly Supervised Deep Neural Network
by: Yang Wu, et al.
Published: (2019-11-01)