Research Advances in Deep Learning for Image Semantic Segmentation Techniques DOI Creative Commons
Zhiguo Xiao, Tengfei Chai,

Nianfeng Li

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 175715 - 175741

Published: Jan. 1, 2024

Language: Английский

Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation DOI
Shiman Li, Haoran Wang,

Yucong Meng

et al.

Physics in Medicine and Biology, Journal Year: 2024, Volume and Issue: 69(11), P. 11TR01 - 11TR01

Published: March 13, 2024

Abstract Precise delineation of multiple organs or abnormal regions in the human body from medical images plays an essential role computer-aided diagnosis, surgical simulation, image-guided interventions, and especially radiotherapy treatment planning. Thus, it is great significance to explore automatic segmentation approaches, among which deep learning-based approaches have evolved rapidly witnessed remarkable progress multi-organ segmentation. However, obtaining appropriately sized fine-grained annotated dataset extremely hard expensive. Such scarce annotation limits development high-performance models but promotes many annotation-efficient learning paradigms. Among these, studies on transfer leveraging external datasets, semi-supervised including unannotated datasets partially-supervised integrating partially-labeled led dominant way break such dilemmas We first review fully supervised method, then present a comprehensive systematic elaboration 3 abovementioned paradigms context both technical methodological perspectives, finally summarize their challenges future trends.

Language: Английский

Citations

5

Misalignment-free progressive hybrid distillation for heterogeneous robust collaborative 3D object detection for smart urban mobility DOI
Peizhou Ni, Benwu Wang,

Kuang Zhao

et al.

Measurement, Journal Year: 2025, Volume and Issue: 248, P. 116920 - 116920

Published: Feb. 7, 2025

Language: Английский

Citations

0

CIT: Rethinking class-incremental semantic segmentation with a Class Independent Transformation DOI Creative Commons
Jinchao Ge, Bowen Zhang, Akide Liu

et al.

Pattern Recognition, Journal Year: 2025, Volume and Issue: 167, P. 111707 - 111707

Published: April 26, 2025

Language: Английский

Citations

0

Flexible wearable/stickable ammonia colorimetric sensors with assistance of deep learning for ammonia leakage monitoring and early warning DOI
Yuling Mao, Dongzhi Zhang,

Hao Zhang

et al.

Chemical Engineering Journal, Journal Year: 2025, Volume and Issue: unknown, P. 163809 - 163809

Published: May 1, 2025

Language: Английский

Citations

0

Learning At a Glance: Towards Interpretable Data-Limited Continual Semantic Segmentation Via Semantic-Invariance Modelling DOI
Bo Yuan, Danpei Zhao, Zhenwei Shi

et al.

IEEE Transactions on Pattern Analysis and Machine Intelligence, Journal Year: 2024, Volume and Issue: 46(12), P. 7909 - 7923

Published: May 6, 2024

Continual semantic segmentation (CSS) based on incremental learning (IL) is a great endeavour in developing human- like models. However, current CSS approaches encounter challenges the trade-off between preserving old knowledge and new ones, where they still need large-scale annotated data for training lack interpretability. In this paper, we present Learning at Glance (LAG), an efficient, robust, interpretable approach CSS. Specifically, LAG simple model-agnostic architecture, yet it achieves competitive efficiency with limited data. Inspired by recognition patterns, propose semantic-invariance modelling via features decoupling that simultaneously reconciles solid inheritance new-term learning. Concretely, proposed manner includes two ways, i.e., channel- wise spatial-level neuron-relevant consistency. Our preserves semantic-invariant as prototypes to alleviate catastrophic forgetting, while also constraining sample-specific contents through asymmetric contrastive method enhance model robustness during IL steps. Experimental results multiple datasets validate effectiveness of method. Furthermore, introduce novel protocol better reflects realistic data-limited settings, superior performance under conditions.

Language: Английский

Citations

2

Research Advances in Deep Learning for Image Semantic Segmentation Techniques DOI Creative Commons
Zhiguo Xiao, Tengfei Chai,

Nianfeng Li

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 175715 - 175741

Published: Jan. 1, 2024

Language: Английский

Citations

1