Instance-Level Contrastive Learning for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD) has received increasing attention in object detection field, because it only requires image-level annotations to indicate the presence or absence of target objects, which greatly reduces the labeling costs. Existing methods usually focus on the current indiv...
Main Authors: | Ming Zhang, Bing Zeng |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/19/7525 |
Similar Items
-
Weakly Supervised Object Detection with Symmetry Context
by: Xinyu Gu, et al.
Published: (2022-09-01) -
WS-RCNN: Learning to Score Proposals for Weakly Supervised Instance Segmentation
by: Jia-Rong Ou, et al.
Published: (2021-05-01) -
Weakly Supervised Object Detection Using Complementary Learning and Instance Clustering
by: Mehwish Awan, et al.
Published: (2020-01-01) -
Weakly Supervised Instance Segmentation Based on Two-Stage Transfer Learning
by: Yongqing Sun, et al.
Published: (2020-01-01) -
DIM: long-tailed object detection and instance segmentation via dynamic instance memory
by: Zhao-Min Chen, et al.
Published: (2023-01-01)