Unsupervised semantic segmentation by distilling feature correspondences
Unsupervised semantic segmentation aims to discover and localize semantically meaningful
categories within image corpora without any form of annotation. To solve this task …
categories within image corpora without any form of annotation. To solve this task …
Weakly supervised semantic segmentation by pixel-to-prototype contrast
Though image-level weakly supervised semantic segmentation (WSSS) has achieved great
progress with Class Activation Maps (CAMs) as the cornerstone, the large supervision gap …
progress with Class Activation Maps (CAMs) as the cornerstone, the large supervision gap …
Weakly-supervised semantic segmentation with superpixel guided local and global consistency
Weakly supervised semantic segmentation task aims to learn a segmentation model with
only image-level annotations. Existing methods generally refine the initial seeds to obtain …
only image-level annotations. Existing methods generally refine the initial seeds to obtain …
Deep learning implementation of image segmentation in agricultural applications: a comprehensive review
L Lei, Q Yang, L Yang, T Shen, R Wang… - Artificial Intelligence …, 2024 - Springer
Image segmentation is a crucial task in computer vision, which divides a digital image into
multiple segments and objects. In agriculture, image segmentation is extensively used for …
multiple segments and objects. In agriculture, image segmentation is extensively used for …
Transformer-based automated segmentation of recycling materials for semantic understanding in construction
Construction sites are incorporating cameras to gather imagery data for project
management. While transformer-based deep models show promise in recognizing …
management. While transformer-based deep models show promise in recognizing …
Light-weight shadow detection via GCN-based annotation strategy and knowledge distillation
W Wu, K Zhou, XD Chen, JH Yong - Computer Vision and Image …, 2022 - Elsevier
This paper discusses shadow detection problem, and proposes a light-weight network to
achieve both accurate detection results and high computation efficiency. Firstly, we begin by …
achieve both accurate detection results and high computation efficiency. Firstly, we begin by …
Graph-Segmenter: graph transformer with boundary-aware attention for semantic segmentation
The transformer-based semantic segmentation approaches, which divide the image into
different regions by sliding windows and model the relation inside each window, have …
different regions by sliding windows and model the relation inside each window, have …
3D PET/CT tumor segmentation based on nnU-Net with GCN refinement
Objective. Whole-body positron emission tomography/computed tomography (PET/CT)
scans are an important tool for diagnosing various malignancies (eg malignant melanoma …
scans are an important tool for diagnosing various malignancies (eg malignant melanoma …
Privobfnet: A weakly supervised semantic segmentation model for data protection
CP Tay, V Subbaraju… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
The use of social media has made it easy to communicate and share information over the
internet. However, it also brings issues such as data privacy leakage, which can be …
internet. However, it also brings issues such as data privacy leakage, which can be …
Isim: Iterative self-improved model for weakly supervised segmentation
C Bircanoglu, N Arica - arXiv preprint arXiv:2211.12455, 2022 - arxiv.org
Weakly Supervised Semantic Segmentation (WSSS) is a challenging task aiming to learn
the segmentation labels from class-level labels. In the literature, exploiting the information …
the segmentation labels from class-level labels. In the literature, exploiting the information …