Patch-based training of fully convolutional network for hyperspectral image classification with sparse point labels
Fully convolutional network (FCN), which has excellent capability for capturing spatial
context, was introduced to improve the performance of hyperspectral image classification …
context, was introduced to improve the performance of hyperspectral image classification …
End-to-end boundary exploration for weakly-supervised semantic segmentation
It is full of challenges for weakly supervised semantic segmentation (WSSS) acquiring the
pixel-level object location with only image-level annotations. Especially, the single-stage …
pixel-level object location with only image-level annotations. Especially, the single-stage …
Joint weakly and fully supervised learning for surface defect segmentation from images
B Hu, X Wang, W Yu - Signal Processing: Image Communication, 2022 - Elsevier
Surface defect segmentation from industrial images based on deep learning has been
rapidly developed in recent years. However, the related methods depend heavily on a large …
rapidly developed in recent years. However, the related methods depend heavily on a large …
Mitigating undisciplined over-smoothing in transformer for weakly supervised semantic segmentation
A surge of interest has emerged in weakly supervised semantic segmentation due to its
remarkable efficiency in recent years. Existing approaches based on transformers mainly …
remarkable efficiency in recent years. Existing approaches based on transformers mainly …
Dual-gradients localization framework for weakly supervised object localization
Weakly Supervised Object Localization (WSOL) aims to learn object locations in a given
image while only using image-level annotations. For highlighting the whole object regions …
image while only using image-level annotations. For highlighting the whole object regions …
Branches Mutual Promotion for End-to-End Weakly Supervised Semantic Segmentation
End-to-end weakly supervised semantic segmentation aims at optimizing a segmentation
model in a single-stage training process based on only image annotations. Existing methods …
model in a single-stage training process based on only image annotations. Existing methods …
Modeling the Label Distributions for Weakly-Supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models by
weak labels, which is receiving significant attention due to its low annotation cost. Existing …
weak labels, which is receiving significant attention due to its low annotation cost. Existing …
EasySpec: Automatic specular reflection detection and suppression from endoscopic images
P Monkam, J Wu, W Lu, W Shan… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
The outcome of endoscopic tasks can be significantly affected by the presence of specular
reflections. Although numerous methods have been proposed for specular reflection …
reflections. Although numerous methods have been proposed for specular reflection …
Dynamic feature regularized loss for weakly supervised semantic segmentation
We focus on tackling weakly supervised semantic segmentation with scribble-level
annotation. The regularized loss has been proven to be an effective solution for this task …
annotation. The regularized loss has been proven to be an effective solution for this task …
Dual progressive transformations for weakly supervised semantic segmentation
Weakly supervised semantic segmentation (WSSS), which aims to mine the object regions
by merely using class-level labels, is a challenging task in computer vision. The current state …
by merely using class-level labels, is a challenging task in computer vision. The current state …