Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives

J Li, J Chen, Y Tang, C Wang, BA Landman… - Medical image …, 2023 - Elsevier
Transformer, one of the latest technological advances of deep learning, has gained
prevalence in natural language processing or computer vision. Since medical imaging bear …

Centralized feature pyramid for object detection

Y Quan, D Zhang, L Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The visual feature pyramid has shown its superiority in both effectiveness and efficiency in a
variety of applications. However, current methods overly focus on inter-layer feature …

A survey of the vision transformers and their CNN-transformer based variants

A Khan, Z Rauf, A Sohail, AR Khan, H Asif… - Artificial Intelligence …, 2023 - Springer
Vision transformers have become popular as a possible substitute to convolutional neural
networks (CNNs) for a variety of computer vision applications. These transformers, with their …

From sam to cams: Exploring segment anything model for weakly supervised semantic segmentation

H Kweon, KJ Yoon - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Abstract Weakly Supervised Semantic Segmentation (WSSS) aims to learn the concept of
segmentation using image-level class labels. Recent WSSS works have shown promising …

Segment anything model (sam) enhanced pseudo labels for weakly supervised semantic segmentation

T Chen, Z Mai, R Li, W Chao - ar** for weakly-supervised semantic segmentation with multi-scale inference
Y Liu, L Lian, E Zhang, L Xu, C **ao… - Frontiers in Computer …, 2022 - frontiersin.org
Deep learning techniques have shown great potential in medical image processing,
particularly through accurate and reliable image segmentation on magnetic resonance …