Weakly-Supervised Object Localization
76 papers with code • 8 benchmarks • 3 datasets
Weakly supervised object localization (WSOL) learns to localize objects with only image-level labels, no object level labels (bonding boxes, etc.,) is needed. It is more attractive since image-level labels are much easier and cheaper to obtain.
Benchmarks
These leaderboards are used to track progress in Weakly-Supervised Object Localization
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Weakly-Supervised Object Localization models and implementations
ImageNet
CUB-200-2011
Tiny ImageNet
Most implemented papers
Learning Deep Features for Discriminative Localization
In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels.
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization
We propose `Hide-and-Seek', a weakly-supervised framework that aims to improve object localization in images and action localization in videos.
Eigen-CAM: Class Activation Map using Principal Components
At the heart of this progress is convolutional neural networks (CNNs) that are capable of learning representations or features given a set of data.
LayerCAM: Exploring Hierarchical Class Activation Maps for Localization
jacobgil/pytorch-grad-cam
•
•
IEEE 2021
To evaluate the quality of the class activation maps produced by LayerCAM, we apply them to weakly-supervised object localization and semantic segmentation.
WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation
durandtibo/wildcat.pytorch
•
•
CVPR 2017
This paper introduces WILDCAT, a deep learning method which jointly aims at aligning image regions for gaining spatial invariance and learning strongly localized features.
Adversarial Complementary Learning for Weakly Supervised Object Localization
junkwhinger/adversarial_complementary_learning
•
•
CVPR 2018
With such an adversarial learning, the two parallel-classifiers are forced to leverage complementary object regions for classification and can finally generate integral object localization together.
Evaluating Weakly Supervised Object Localization Methods Right
clovaai/wsolevaluation
•
•
CVPR 2020
In this paper, we argue that WSOL task is ill-posed with only image-level labels, and propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set.
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets
In this paper, we argue that WSOL task is ill-posed with only image-level labels, and propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set.
A Generic Visualization Approach for Convolutional Neural Networks
ahmdtaha/l2_caf_pytorch
•
•
ECCV 2020
Compared to classification networks, attention visualization for retrieval networks is hardly studied.
TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization
vasgaowei/TS-CAM
•
•
ICCV 2021
TS-CAM finally couples the patch tokens with the semantic-agnostic attention map to achieve semantic-aware localization.
