Weakly supervised object localization and detection: A survey
As an emerging and challenging problem in the computer vision community, weakly
supervised object localization and detection plays an important role for develo** new …
supervised object localization and detection plays an important role for develo** new …
Layercam: Exploring hierarchical class activation maps for localization
The class activation maps are generated from the final convolutional layer of CNN. They can
highlight discriminative object regions for the class of interest. These discovered object …
highlight discriminative object regions for the class of interest. These discovered object …
Lesion-aware transformers for diabetic retinopathy grading
Diabetic retinopathy (DR) is the leading cause of permanent blindness in the working-age
population. And automatic DR diagnosis can assist ophthalmologists to design tailored …
population. And automatic DR diagnosis can assist ophthalmologists to design tailored …
Class attention transfer based knowledge distillation
Previous knowledge distillation methods have shown their impressive performance on
model compression tasks, however, it is hard to explain how the knowledge they transferred …
model compression tasks, however, it is hard to explain how the knowledge they transferred …
Shallow feature matters for weakly supervised object localization
Weakly supervised object localization (WSOL) aims to localize objects by only utilizing
image-level labels. Class activation maps (CAMs) are the commonly used features to …
image-level labels. Class activation maps (CAMs) are the commonly used features to …
Foreground activation maps for weakly supervised object localization
Weakly supervised object localization (WSOL) aims to localize objects with only image-level
labels, which has better scalability and practicability than fully supervised methods in the …
labels, which has better scalability and practicability than fully supervised methods in the …
Deep learning for weakly-supervised object detection and localization: A survey
Abstract Weakly-Supervised Object Detection (WSOD) and Localization (WSOL), ie.,
detecting multiple and single instances with bounding boxes in an image using image-level …
detecting multiple and single instances with bounding boxes in an image using image-level …
Weakly supervised object detection for remote sensing images: A survey
The rapid development of remote sensing technologies and the availability of many satellite
and aerial sensors have boosted the collection of large volumes of high-resolution images …
and aerial sensors have boosted the collection of large volumes of high-resolution images …
Generalized weakly supervised object localization
D Zhang, G Guo, W Zeng, L Li… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
With the goal of learning to localize specific object semantics using the low-cost image-level
annotation, weakly supervised object localization (WSOL) has been receiving increasing …
annotation, weakly supervised object localization (WSOL) has been receiving increasing …
Background activation suppression for weakly supervised object localization
Weakly supervised object localization (WSOL) aims to localize objects using only image-
level labels. Recently a new paradigm has emerged by generating a foreground prediction …
level labels. Recently a new paradigm has emerged by generating a foreground prediction …