Segmentation Accuracy
Segmentation accuracy, the precision of delineating objects or regions within images, is a crucial aspect of many fields, particularly medical image analysis and remote sensing. Current research focuses on improving accuracy through advanced model architectures like U-Net and its variants, Transformers, and novel loss functions designed to address challenges such as class imbalance and small object detection. These advancements are driving improvements in diagnostic accuracy, treatment planning, and automated analysis across diverse applications, impacting both scientific understanding and practical outcomes.
Papers
Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincar\'e Ball
Simon Weber, Barış Zöngür, Nikita Araslanov, Daniel Cremers
LiteNeXt: A Novel Lightweight ConvMixer-based Model with Self-embedding Representation Parallel for Medical Image Segmentation
Ngoc-Du Tran, Thi-Thao Tran, Quang-Huy Nguyen, Manh-Hung Vu, Van-Truong Pham