Technology Category
Machine Learning: Transfer, Domain Adaptation, Multi-Task LearningComputer Vision: SegmentationSearch and Optimization: Mixed Discrete/Continuous Search
DAWN: Domain-Adaptive Weakly Supervised Nuclei Segmentation via Cross-Task Interactions
🤖 AI Summary
To address low-quality pseudo-labels and poor cross-domain generalization in weakly supervised nucleus segmentation, this paper proposes an end-to-end cross-task interactive domain adaptation framework. Methodologically: (1) it introduces the first detection-assisted segmentation mechanism with cross-task feature interaction to jointly enhance localization accuracy and boundary modeling; (2) it designs a source-prior-guided consistency constraint to improve feature-level domain invariance; and (3) it incorporates dynamic pseudo-label optimization coupled with interactive joint training to mitigate error accumulation. Evaluated on six histopathological image datasets, the method significantly outperforms existing weakly supervised approaches and achieves performance on par with—or even surpassing—that of fully supervised baselines. These results validate its robust domain adaptability and strong generalization capability across diverse pathological domains.
Technology Category
Application Category
📝 Abstract
Weakly supervised segmentation methods have gained significant attention due to their ability to reduce the reliance on costly pixel-level annotations during model training. However, the current weakly supervised nuclei segmentation approaches typically follow a two-stage pseudo-label generation and network training process. The performance of the nuclei segmentation heavily relies on the quality of the generated pseudo-labels, thereby limiting its effectiveness. This paper introduces a novel domain-adaptive weakly supervised nuclei segmentation framework using cross-task interaction strategies to overcome the challenge of pseudo-label generation. Specifically, we utilize weakly annotated data to train an auxiliary detection task, which assists the domain adaptation of the segmentation network. To enhance the efficiency of domain adaptation, we design a consistent feature constraint module integrating prior knowledge from the source domain. Furthermore, we develop pseudo-label optimization and interactive training methods to improve the domain transfer capability. To validate the effectiveness of our proposed method, we conduct extensive comparative and ablation experiments on six datasets. The results demonstrate the superiority of our approach over existing weakly supervised approaches. Remarkably, our method achieves comparable or even better performance than fully supervised methods. Our code will be released in https://github.com/zhangye-zoe/DAWN.
Problem
Research questions and friction points this paper is trying to address.
Weakly Supervised Learning
Nuclear Segmentation
Pseudo Label Accuracy
Innovation
Methods, ideas, or system contributions that make the work stand out.
DAWN
Cross-task Interaction Strategy
Weak Supervision
🔎 Similar Papers
No similar papers found.
