# Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing

arXiv: https://arxiv.org/abs/2401.03043 · HTML: https://mlsanity.com/paper/2401.03043/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 5 Jan 2024.

## Builds on (most cited first, 10 of 10)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Optimal Feature Transport for Cross-View Image Geo-Localization](https://mlsanity.com/paper/1907.05021/) (2019)
- [Superhuman Accuracy on the SNEMI3D Connectomics Challenge](https://mlsanity.com/paper/1706.00120/) (2017)
- [AxonEM Dataset: 3D Axon Instance Segmentation of Brain Cortical Regions](https://mlsanity.com/paper/2107.05451/) (2021)
- [Learning and Segmenting Dense Voxel Embeddings for 3D Neuron Reconstruction](https://mlsanity.com/paper/1909.09872/) (2019)
- [An Error Detection and Correction Framework for Connectomics](https://mlsanity.com/paper/1708.02599/) (2017)

## Built on by (most cited first, 4 of 4)

- [Autoproof: Automated Segmentation Proofreading for Connectomics](https://mlsanity.com/paper/2509.26585/) (2025)
- [ConnectomeBench2: A Unified Benchmark for Automated Connectomic Proofreading](https://mlsanity.com/paper/2606.21116/) (2026)
- [SkelEM: Training-Signal Decoupling of Skeleton and Diffusion for Self-supervised Axial Super-Resolution in Volume Microscopy](https://mlsanity.com/paper/2606.30012/) (2026)
- [Probe-EM: Targeted Neuron Tracing via Training-Free Semantic Verification](https://mlsanity.com/paper/2607.04696/) (2026)

## Abstract (arXiv)

The current neuron reconstruction pipeline for electron microscopy (EM) data usually includes automatic image segmentation followed by extensive human expert proofreading. In this work, we aim to reduce human workload by predicting connectivity between over-segmented neuron pieces, taking both microscopy image and 3D morphology features into account, similar to human proofreading workflow. To this end, we first construct a dataset, named FlyTracing, that contains millions of pairwise connections of segments expanding the whole fly brain, which is three orders of magnitude larger than existing datasets for neuron segment connection. To learn sophisticated biological imaging features from the connectivity annotations, we propose a novel connectivity-aware contrastive learning method to generate dense volumetric EM image embedding. The learned embeddings can be easily incorporated with any point or voxel-based morphological representations for automatic neuron tracing. Extensive comparisons of different combination schemes of image and morphological representation in identifying split errors across the whole fly brain demonstrate the superiority of the proposed approach, especially for the locations that contain severe imaging artifacts, such as section missing and misalignment. The dataset and code are available at https://github.com/Levishery/Flywire-Neuron-Tracing.