Weakly supervised object localization and detection: A survey

D Zhang, J Han, G Cheng… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
As an emerging and challenging problem in the computer vision community, weakly
supervised object localization and detection plays an important role for develo** new …

Layercam: Exploring hierarchical class activation maps for localization

PT Jiang, CB Zhang, Q Hou… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
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 …

Lesion-aware transformers for diabetic retinopathy grading

R Sun, Y Li, T Zhang, Z Mao, F Wu… - Proceedings of the …, 2021 - openaccess.thecvf.com
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 …

Class attention transfer based knowledge distillation

Z Guo, H Yan, H Li, X Lin - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Previous knowledge distillation methods have shown their impressive performance on
model compression tasks, however, it is hard to explain how the knowledge they transferred …

Shallow feature matters for weakly supervised object localization

J Wei, Q Wang, Z Li, S Wang… - Proceedings of the …, 2021 - openaccess.thecvf.com
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 …

Foreground activation maps for weakly supervised object localization

M Meng, T Zhang, Q Tian… - Proceedings of the …, 2021 - openaccess.thecvf.com
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 …

Deep learning for weakly-supervised object detection and localization: A survey

F Shao, L Chen, J Shao, W Ji, S **ao, L Ye, Y Zhuang… - Neurocomputing, 2022 - Elsevier
Abstract Weakly-Supervised Object Detection (WSOD) and Localization (WSOL), ie.,
detecting multiple and single instances with bounding boxes in an image using image-level …

Weakly supervised object detection for remote sensing images: A survey

C Fasana, S Pasini, F Milani, P Fraternali - Remote Sensing, 2022 - mdpi.com
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 …

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 …

Background activation suppression for weakly supervised object localization

P Wu, W Zhai, Y Cao - 2022 IEEE/CVF Conference on …, 2022 - ieeexplore.ieee.org
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 …