Instance segmentation with the number of clusters incorporated in embedding learning
This work addresses a specific problem in medical image analysis for instance segmentation, offering an incremental improvement by simplifying post-processing.
The paper tackles the error accumulation in multi-stage instance segmentation by proposing FCRNet, a one-stage method that incorporates the number of clusters into embedding learning, achieving superior performance on the BBBC006 nucleus dataset.
Semantic and instance segmentation algorithms are two general yet distinct image segmentation solutions powered by Convolution Neural Network. While semantic segmentation benefits extensively from the end-to-end training strategy, instance segmentation is frequently framed as a multi-stage task, supported by learning-based discrimination and post-process clustering. Independent optimizations on substages instigate the accumulation of segmentation errors. In this work, we propose to embed prior clustering information into an embedding learning framework FCRNet, stimulating the one-stage instance segmentation. FCRNet relieves the complexity of post process by incorporating the number of clustering groups into the embedding space. The superior performance of FCRNet is verified and compared with other methods on the nucleus dataset BBBC006.