Browse > Computer Vision > Object Localization > Weakly-Supervised Object Localization

Weakly-Supervised Object Localization

11 papers with code · Computer Vision
Subtask of Object Localization

State-of-the-art leaderboards

Greatest papers with code

WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation

CVPR 2017 durandtibo/wildcat.pytorch

This paper introduces WILDCAT, a deep learning method which jointly aims at aligning image regions for gaining spatial invariance and learning strongly localized features.

IMAGE CLASSIFICATION SEMANTIC SEGMENTATION WEAKLY-SUPERVISED OBJECT LOCALIZATION

Soft Proposal Networks for Weakly Supervised Object Localization

ICCV 2017 yeezhu/SPN.pytorch

Weakly supervised object localization remains challenging, where only image labels instead of bounding boxes are available during training.

WEAKLY SUPERVISED OBJECT DETECTION WEAKLY-SUPERVISED OBJECT LOCALIZATION

Attention-based Dropout Layer for Weakly Supervised Object Localization

CVPR 2019 junsukchoe/ADL

Weakly Supervised Object Localization (WSOL) techniques learn the object location only using image-level labels, without location annotations.

WEAKLY-SUPERVISED OBJECT LOCALIZATION

Attention-Based Dropout Layer for Weakly Supervised Object Localization

CVPR 2019 junsukchoe/ADL

Weakly Supervised Object Localization (WSOL) techniques learn the object location only using image-level labels, without location annotations.

WEAKLY-SUPERVISED OBJECT LOCALIZATION

C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection

CVPR 2019 Winfrand/C-MIL

Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detectors.

MULTIPLE INSTANCE LEARNING WEAKLY SUPERVISED OBJECT DETECTION WEAKLY-SUPERVISED OBJECT LOCALIZATION

Min-Entropy Latent Model for Weakly Supervised Object Detection

CVPR 2018 WinFrand/MELM

Weakly supervised object detection is a challenging task when provided with image category supervision but required to learn, at the same time, object locations and object detectors.

IMAGE CLASSIFICATION WEAKLY SUPERVISED OBJECT DETECTION WEAKLY-SUPERVISED OBJECT LOCALIZATION

Adversarial Complementary Learning for Weakly Supervised Object Localization

CVPR 2018 junkwhinger/adversarial_complementary_learning

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.

WEAKLY-SUPERVISED OBJECT LOCALIZATION