Online active proposal set generation for weakly supervised object detection
To reduce the manpower consumption on box-level annotations, many weakly supervised object detection methods which only require image-level annotations, have been proposed recently. The training process in these methods is formulated into two steps. They firstly train a neural network under weak sup...
Main Authors: | Jin, Ruibing, Lin, Guosheng, Wen, Changyun |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Journal Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/161623 |
Similar Items
-
Motion context network for weakly supervised object detection in videos
by: Jin, Ruibing, et al.
Published: (2022) -
Enhancing Cervical Cell Detection Through Weakly Supervised Learning With Local Distillation Mechanism
by: Juanjuan Yin, et al.
Published: (2024-01-01) -
Feature flow: in-network feature flow estimation for video object detection
by: Jin, Ruibing, et al.
Published: (2022) -
Weakly supervised salient object detection via bounding-box annotation and SAM model
by: Xiangquan Liu, et al.
Published: (2024-02-01) -
Weakly supervised video anomaly detection based on hyperbolic space
by: Meilin Qi, et al.
Published: (2024-11-01)