Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning

Authors: Yinda Chen, Wei Huang, Shenglong Zhou, Qi Chen, Zhiwei Xiong

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 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.
Researcher Affiliation Academia Yinda Chen1,2 , Wei Huang1 , Shenglong Zhou1 , Qi Chen1 , Zhiwei Xiong1,2, 1University of Science and Technology of China 2Institute of Artificial Intelligence, Hefei Comprehensive National Science Center {cyd0806, weih527, slzhou96, qic}@mail.ustc.edu.cn, zwxiong@ustc.edu.cn
Pseudocode No The paper describes the methods in prose and uses diagrams, but does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes Code is available at https://github.com/ydchen0806/db Mi M.
Open Datasets Yes The Full Adult Fly Brain (FAFB) dataset [Zheng et al., 2018] is a highly valuable resource for neuroinformatics research, offering a comprehensive and detailed view of the neural architecture of the Drosophila melanogaster (fruit fly) brain.
Dataset Splits Yes Each sub-volume has 125 slices of 1250 1250 images, and we choose the first 60 slices for training, 15 slices for validation, and the remaining 50 slices for testing
Hardware Specification Yes perform batch size 16 pretraining on 8 RTX 3090s.
Software Dependencies No The paper mentions software components such as Vi T, UNETR, and the Adam optimizer, but does not provide specific version numbers for any of these dependencies.
Experiment Setup Yes We use the Adam optimizer in both the pretraining and fine-tuning phases, with β1 = 0.9, β2 = 0.999. The only difference lies in the pretraining process, where we set the learning rate to 0.0001 and perform batch size 16 pretraining on 8 RTX 3090s. In the fine-tuning phase, we adopt a Layerwise Learning Rate Decay (LLRD) training method, which adjusts the learning rate layer by layer during training. We set the learning rate of the last layer s parameters to 0.001 and the learning rate of the previous layer s parameters to 0.95 times the learning rate of the next layer s parameters.