aiqbench analysis
This research presents Active-DiNTS, a method that integrates active learning with differentiable network topology search to optimize 3D medical image segmentation. By jointly refining model weights and architecture while curating labels from unlabeled MRI data, the approach achieves significant accuracy gains on the BrainTumour benchmark using only a single GPU and a fraction of the labeled data required by prior methods. The study demonstrates that pairing differentiable NAS with active data acquisition offers a practical pathway for deploying high-performance segmentation models under realistic computational and annotation constraints.
Active-DiNTS: Active Differentiable Network Topology Search
arXiv:2610.04787v1 Announce Type: cross Abstract: Neural Architecture Search (NAS) has proved to be a strong alternative to manual network design, but applying it to 3D medical image segmentation is limited by two well-known costs, large annotation budgets and multi-GPU clusters. Thus, this paper introduces Active-DiNTS (Active Differentiable Network Topology Search), an approach that embeds pool-based Active Learning (AL) into a bi-level differentiable topology search to perform architecture discovery and label curation jointly. At each query round, unlabeled MRI volumes are ranked by one of three uncertainty signals (Entropy, Variance, or Standard Deviation), and only the top-ranked volumes are sent to an oracle for annotation. The new labels feed two interlocked stages. Network weights are updated in an outer loop, while the macro/micro topology of a U-Net-style backbone is refined in an inner loop. Three AL regimes (weights-only, topology-only, joint) expose the speed-accuracy trade-off. Evaluations on the Medical Segmentation Decathlon (MSD) Task01 BrainTumour benchmark showed that Active-DiNTS surpasses DiNTS, C2FNAS, and nnU-Net in Dice, with gains of about 10 percentage points on Edema and 5 points on Non-Enhancing core, on a single GPU and using a fraction of the labeled volumes. The discovered architectures are denser and more FLOP-heavy than prior baselines, but remain competitive in trainable parameters and peak memory; the fastest search variant finishes in under 0.25 GPU-days, over 27x faster than the eight-GPU DiNTS search. Together, these results indicate that pairing differentiable NAS with active data acquisition is a practical recipe for accurate 3D segmentation under realistic constraints.
Abstract:Neural Architecture Search (NAS) has proved to be a strong alternative to manual network design, but applying it to 3D medical image segmentation is limited by two well-known costs, large annotation budgets and multi-GPU clusters. Thus, this paper introduces Active-DiNTS (Active Differentiable Network Topology Search), an approach that embeds pool-based Active Learning (AL) into a bi-level differentiable topology search to perform architecture discovery and label curation jointly. At each query round, unlabeled MRI volumes are ranked by one of three uncertainty signals (Entropy, Variance, or Standard Deviation), and only the top-ranked volumes are sent to an oracle for annotation. The new labels feed two interlocked stages. Network weights are updated in an outer loop, while the macro/micro topology of a U-Net-style backbone is refined in an inner loop. Three AL regimes (weights-only, topology-only, joint) expose the speed-accuracy trade-off. Evaluations on the Medical Segmentation Decathlon (MSD) Task01 BrainTumour benchmark showed that Active-DiNTS surpasses DiNTS, C2FNAS, and nnU-Net in Dice, with gains of about 10 percentage points on Edema and 5 points on Non-Enhancing core, on a single GPU and using a fraction of the labeled volumes. The discovered architectures are denser and more FLOP-heavy than prior baselines, but remain competitive in trainable parameters and peak memory; the fastest search variant finishes in under 0.25 GPU-days, over 27x faster than the eight-GPU DiNTS search. Together, these results indicate that pairing differentiable NAS with active data acquisition is a practical recipe for accurate 3D segmentation under realistic constraints.
19 pages, 7 figures, 3 tables. Extends material from the first author's PhD thesis (University of Sao Paulo / La Rochelle Universite, 2024)
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
arXiv:2610.04787 [cs.CV]
(or arXiv:2610.04787v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.04787 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 376 words
Related coverage
Learning Coherent Representations: A Topological Approach to Interpretability
arXiv · Jun 3, 2026
Building Blocks for Foundation Model Training and Inference on AWS
Hugging Face · May 11, 2026
[AINews] High Taste Testers Ep. 1
Latent Space · Oct 17, 2026
Challenge: Hand coding weights for efficient sequence memorisation
AI Alignment Forum · Jul 23, 2026