Instance-Aware Pseudo-Labeling and Class-Focused Contrastive Learning for Weakly Supervised Domain Adaptive Segmentation of Electron Microscopy
By: Shan Xiong , Jiabao Chen , Ye Wang and more
Potential Business Impact:
Helps scientists see tiny cell parts faster.
Annotation-efficient segmentation of the numerous mitochondria instances from various electron microscopy (EM) images is highly valuable for biological and neuroscience research. Although unsupervised domain adaptation (UDA) methods can help mitigate domain shifts and reduce the high costs of annotating each domain, they typically have relatively low performance in practical applications. Thus, we investigate weakly supervised domain adaptation (WDA) that utilizes additional sparse point labels on the target domain, which require minimal annotation effort and minimal expert knowledge. To take full use of the incomplete and imprecise point annotations, we introduce a multitask learning framework that jointly conducts segmentation and center detection with a novel cross-teaching mechanism and class-focused cross-domain contrastive learning. While leveraging unlabeled image regions is essential, we introduce segmentation self-training with a novel instance-aware pseudo-label (IPL) selection strategy. Unlike existing methods that typically rely on pixel-wise pseudo-label filtering, the IPL semantically selects reliable and diverse pseudo-labels with the help of the detection task. Comprehensive validations and comparisons on challenging datasets demonstrate that our method outperforms existing UDA and WDA methods, significantly narrowing the performance gap with the supervised upper bound. Furthermore, under the UDA setting, our method also achieves substantial improvements over other UDA techniques.
Similar Papers
Balanced Learning for Domain Adaptive Semantic Segmentation
CV and Pattern Recognition
Helps computers better understand pictures of things.
Prompt-DAS: Annotation-Efficient Prompt Learning for Domain Adaptive Semantic Segmentation of Electron Microscopy Images
CV and Pattern Recognition
Helps computers find tiny parts inside cells.
LPD: Learnable Prototypes with Diversity Regularization for Weakly Supervised Histopathology Segmentation
CV and Pattern Recognition
Finds cancer cells better in pictures.