SegMate: Asymmetric Attention-Based Lightweight Architecture for Efficient Multi-Organ Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bunea, Andrei-Alexandru, Popovici, Dan-Matei, Ionescu, Radu Tudor
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917299616743424
author Bunea, Andrei-Alexandru
Popovici, Dan-Matei
Ionescu, Radu Tudor
author_facet Bunea, Andrei-Alexandru
Popovici, Dan-Matei
Ionescu, Radu Tudor
contents State-of-the-art models for medical image segmentation achieve excellent accuracy but require substantial computational resources, limiting deployment in resource-constrained clinical settings. We present SegMate, an efficient 2.5D framework that achieves state-of-the-art accuracy, while considerably reducing computational requirements. Our efficient design is the result of meticulously integrating asymmetric architectures, attention mechanisms, multi-scale feature fusion, slice-based positional conditioning, and multi-task optimization. We demonstrate the efficiency-accuracy trade-off of our framework across three modern backbones (EfficientNetV2-M, MambaOut-Tiny, FastViT-T12). We perform experiments on three datasets: TotalSegmentator, SegTHOR and AMOS22. Compared with the vanilla models, SegMate reduces computation (GFLOPs) by up to 2.5x and memory footprint (VRAM) by up to 2.1x, while generally registering performance gains of around 1%. On TotalSegmentator, we achieve a Dice score of 93.51% with only 295MB peak GPU memory. Zero-shot cross-dataset evaluations on SegTHOR and AMOS22 demonstrate strong generalization, with Dice scores of up to 86.85% and 89.35%, respectively. We release our open-source code at https://github.com/andreibunea99/SegMate.
format Preprint
id arxiv_https___arxiv_org_abs_2602_23903
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SegMate: Asymmetric Attention-Based Lightweight Architecture for Efficient Multi-Organ Segmentation
Bunea, Andrei-Alexandru
Popovici, Dan-Matei
Ionescu, Radu Tudor
Computer Vision and Pattern Recognition
Machine Learning
State-of-the-art models for medical image segmentation achieve excellent accuracy but require substantial computational resources, limiting deployment in resource-constrained clinical settings. We present SegMate, an efficient 2.5D framework that achieves state-of-the-art accuracy, while considerably reducing computational requirements. Our efficient design is the result of meticulously integrating asymmetric architectures, attention mechanisms, multi-scale feature fusion, slice-based positional conditioning, and multi-task optimization. We demonstrate the efficiency-accuracy trade-off of our framework across three modern backbones (EfficientNetV2-M, MambaOut-Tiny, FastViT-T12). We perform experiments on three datasets: TotalSegmentator, SegTHOR and AMOS22. Compared with the vanilla models, SegMate reduces computation (GFLOPs) by up to 2.5x and memory footprint (VRAM) by up to 2.1x, while generally registering performance gains of around 1%. On TotalSegmentator, we achieve a Dice score of 93.51% with only 295MB peak GPU memory. Zero-shot cross-dataset evaluations on SegTHOR and AMOS22 demonstrate strong generalization, with Dice scores of up to 86.85% and 89.35%, respectively. We release our open-source code at https://github.com/andreibunea99/SegMate.
title SegMate: Asymmetric Attention-Based Lightweight Architecture for Efficient Multi-Organ Segmentation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2602.23903