Segmentation Model
Segmentation models aim to partition images into meaningful regions, a crucial task across diverse fields like medical imaging and autonomous driving. Current research emphasizes improving model robustness and efficiency, focusing on architectures like U-Nets, Transformers, and diffusion models, often incorporating techniques like continual learning and prompt engineering to adapt to new data or tasks with minimal retraining. These advancements are driving improvements in accuracy and reducing the need for extensive labeled datasets, leading to wider applicability in various scientific and industrial applications.
Papers
Beyond Discriminative Regions: Saliency Maps as Alternatives to CAMs for Weakly Supervised Semantic Segmentation
M. Maruf, Arka Daw, Amartya Dutta, Jie Bu, Anuj Karpatne
SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression
Qingwen Bu, Sungrae Park, Minsoo Khang, Yichuan Cheng
Exploring Transfer Learning in Medical Image Segmentation using Vision-Language Models
Kanchan Poudel, Manish Dhakal, Prasiddha Bhandari, Rabin Adhikari, Safal Thapaliya, Bishesh Khanal
Confidence Contours: Uncertainty-Aware Annotation for Medical Semantic Segmentation
Andre Ye, Quan Ze Chen, Amy Zhang
SegMatch: A semi-supervised learning method for surgical instrument segmentation
Meng Wei, Charlie Budd, Luis C. Garcia-Peraza-Herrera, Reuben Dorent, Miaojing Shi, Tom Vercauteren
Branches Mutual Promotion for End-to-End Weakly Supervised Semantic Segmentation
Lei Zhu, Hangzhou He, Xinliang Zhang, Qian Chen, Shuang Zeng, Qiushi Ren, Yanye Lu
Dimensionality Reduction for Improving Out-of-Distribution Detection in Medical Image Segmentation
McKell Woodland, Nihil Patel, Mais Al Taie, Joshua P. Yung, Tucker J. Netherton, Ankit B. Patel, Kristy K. Brock
Prototype Learning for Out-of-Distribution Polyp Segmentation
Nikhil Kumar Tomar, Debesh Jha, Ulas Bagci