CVAIAug 19, 2023

Learning Multiscale Consistency for Self-supervised Electron Microscopy Instance Segmentation

arXiv:2308.09917v327 citationsh-index: 49
Originality Incremental advance
AI Analysis

This work addresses the challenge of complex shapes and sparse annotations in electron microscopy instance segmentation, offering a domain-specific solution that is incremental in nature.

The paper tackles the problem of instance segmentation in electron microscopy volumes by proposing a self-supervised pretraining framework that enhances multiscale consistency, resulting in significant improvements in downstream tasks like neuron and mitochondria segmentation, especially with limited finetuning data.

Instance segmentation in electron microscopy (EM) volumes is tough due to complex shapes and sparse annotations. Self-supervised learning helps but still struggles with intricate visual patterns in EM. To address this, we propose a pretraining framework that enhances multiscale consistency in EM volumes. Our approach leverages a Siamese network architecture, integrating both strong and weak data augmentations to effectively extract multiscale features. We uphold voxel-level coherence by reconstructing the original input data from these augmented instances. Furthermore, we incorporate cross-attention mechanisms to facilitate fine-grained feature alignment between these augmentations. Finally, we apply contrastive learning techniques across a feature pyramid, allowing us to distill distinctive representations spanning various scales. After pretraining on four large-scale EM datasets, our framework significantly improves downstream tasks like neuron and mitochondria segmentation, especially with limited finetuning data. It effectively captures voxel and feature consistency, showing promise for learning transferable representations for EM analysis.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes