Instance Segmentation of Biomedical Images with an Object-aware Embedding Learned with Local Constraints
This work addresses instance segmentation for biomedical applications, offering an incremental improvement over existing methods by reducing object fusion in crowded conditions.
The paper tackles the problem of instance segmentation in biomedical images, particularly in crowded scenes where existing methods merge or suppress objects, by learning an object-aware embedding with local constraints to separate adjacent objects, achieving state-of-the-art results on cell and leaf segmentation datasets.
Automatic instance segmentation is a problem that occurs in many biomedical applications. State-of-the-art approaches either perform semantic segmentation or refine object bounding boxes obtained from detection methods. Both suffer from crowded objects to varying degrees, merging adjacent objects or suppressing a valid object. In this work, we assign an embedding vector to each pixel through a deep neural network. The network is trained to output embedding vectors of similar directions for pixels from the same object, while adjacent objects are orthogonal in the embedding space, which effectively avoids the fusion of objects in a crowd. Our method yields state-of-the-art results even with a light-weighted backbone network on a cell segmentation (BBBC006 + DSB2018) and a leaf segmentation data set (CVPPP2017). The code and model weights are public available.