Weakly Supervised Object Detection
51 papers with code • 17 benchmarks • 13 datasets
Weakly Supervised Object Detection (WSOD) is the task of training object detectors with only image tag supervisions.
( Image credit: Soft Proposal Networks for Weakly Supervised Object Localization )
Benchmarks
These leaderboards are used to track progress in Weakly Supervised Object Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Weakly Supervised Object Detection models and implementationsDatasets
ImageNet
MS COCO
Charades
Foggy Cityscapes
HICO-DET
PASCAL VOC 2007
PASCAL VOC 2012 test
Clipart1k
Latest papers
Weakly Supervised Rotation-Invariant Aerial Object Detection Network
Object rotation is among long-standing, yet still unexplored, hard issues encountered in the task of weakly supervised object detection (WSOD) from aerial images.
H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object Detection
xuyunqiu/h2fa_r-cnn
•
•
CVPR 2022
How to align the source and target domains is critical to the CDWSOD accuracy.
Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters
DongSky/lbba_boosted_wsod
•
•
ICCV 2021
In this paper, we defend the problem setting for improving localization performance by leveraging the bounding box regression knowledge from a well-annotated auxiliary dataset.
UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object Detection
shenyunhang/UWSOD
•
•
NeurIPS 2020
In this paper, we propose a unified WSOD framework, termed UWSOD, to develop a high-capacity general detection model with only image-level labels, which is self-contained and does not require external modules or additional supervision.
Domain-Adaptive Object Detection via Uncertainty-Aware Distribution Alignment
basiclab/DA-OD-MEAA-PyTorch
•
•
Domain adaptation aims to transfer knowledge from the sourcedata with annotations to scarcely-labeled data in the target domain, which has attracted a lot of attention in recent years and facilitatedmany multimedia applications.
Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection
DeLightCMU/CASD
•
•
NeurIPS 2020
Moreover, the image-level category labels do not enforce consistent object detection across different transformations of the same images.
Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts
nicaogr/Mi_max
•
•
Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years.
Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer
mikuhatsune/wsod_transfer
•
•
ECCV 2020
In this paper, we propose an effective knowledge transfer framework to boost the weakly supervised object detection accuracy with the help of an external fully-annotated source dataset, whose categories may not overlap with the target domain.
Distilling Knowledge from Refinement in Multiple Instance Detection Networks
Then, we present an adaptive supervision aggregation function that dynamically changes the aggregation criteria for selecting boxes related to one of the ground-truth classes, background, or even ignored during the generation of each refinement module supervision.
Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection
NVlabs/wetectron
•
•
CVPR 2020
Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training.
