# NeuroADDA: Active Discriminative Domain Adaptation in Connectomic

arXiv: https://arxiv.org/abs/2503.06196 · HTML: https://mlsanity.com/paper/2503.06196/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 8 Mar 2025.

## Builds on (most cited first, 12 of 12)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Joint Distribution Optimal Transportation for Domain Adaptation](https://mlsanity.com/paper/1705.08848/) (2017)
- [Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings](https://mlsanity.com/paper/2010.08666/) (2020)
- [Superhuman Accuracy on the SNEMI3D Connectomics Challenge](https://mlsanity.com/paper/1706.00120/) (2017)
- [A Transfer Learning Based Active Learning Framework for Brain Tumor Classification](https://mlsanity.com/paper/2011.09265/) (2020)
- [Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics](https://mlsanity.com/paper/1812.01157/) (2018)
- [Wasserstein Distances, Neuronal Entanglement, and Sparsity](https://mlsanity.com/paper/2405.15756/) (2024)
- [Cost-efficient segmentation of electron microscopy images using active learning](https://mlsanity.com/paper/1911.05548/) (2019)
- [Deep learning based domain adaptation for mitochondria segmentation on EM volumes](https://mlsanity.com/paper/2202.10773/) (2022)

## Abstract (arXiv)

Training segmentation models from scratch has been the standard approach for new electron microscopy connectomics datasets. However, leveraging pretrained models from existing datasets could improve efficiency and performance in constrained annotation budget. In this study, we investigate domain adaptation in connectomics by analyzing six major datasets spanning different organisms. We show that, Maximum Mean Discrepancy (MMD) between neuron image distributions serves as a reliable indicator of transferability, and identifies the optimal source domain for transfer learning. Building on this, we introduce NeuroADDA, a method that combines optimal domain selection with source-free active learning to effectively adapt pretrained backbones to a new dataset. NeuroADDA consistently outperforms training from scratch across diverse datasets and fine-tuning sample sizes, with the largest gain observed at n=4 samples with a 25-67% reduction in Variation of Information. Finally, we show that our analysis of distributional differences among neuron images from multiple species in a learned feature space reveals that these domain "distances" correlate with phylogenetic distance among those species.