Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning

TL;DR

This paper introduces a multi-agent reinforcement learning approach to optimize mask image modeling for self-supervised neuron segmentation in electron microscopy data, improving performance over existing methods.

Contribution

It proposes a decision-based MIM framework with multi-agent RL to adaptively select masking strategies, capturing voxel dependencies for better neuron segmentation.

Findings

Outperforms alternative self-supervised methods on EM datasets

Effective in capturing voxel dependencies for segmentation

Demonstrates significant advantage in neuron segmentation tasks

Abstract

The performance of existing supervised neuron segmentation methods is highly dependent on the number of accurate annotations, especially when applied to large scale electron microscopy (EM) data. By extracting semantic information from unlabeled data, self-supervised methods can improve the performance of downstream tasks, among which the mask image model (MIM) has been widely used due to its simplicity and effectiveness in recovering original information from masked images. However, due to the high degree of structural locality in EM images, as well as the existence of considerable noise, many voxels contain little discriminative information, making MIM pretraining inefficient on the neuron segmentation task. To overcome this challenge, we propose a decision-based MIM that utilizes reinforcement learning (RL) to automatically search for optimal image masking ratio and masking strategy. Due to the vast exploration space, using single-agent RL for voxel prediction is impractical. Therefore, we treat each input patch as an agent with a shared behavior policy, allowing for multi-agent collaboration. Furthermore, this multi-agent model can capture dependencies between voxels, which is beneficial for the downstream segmentation task. Experiments conducted on representative EM datasets demonstrate that our approach has a significant advantage over alternative self-supervised methods on the task of neuron segmentation. Code is available at \url{https://github.com/ydchen0806/dbMiM}.