AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation

Jinpeng Lu, Linghan Cai, Yinda Chen, Guo Tang, Songhan Jiang, Haoyuan Shi, Zhiwei Xiong

ICLR 2026 · Architectures and efficiency › CNN design · approach: Dense matching and estimation CNNs

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Gram-matrix supervision (SDKT) from texture teacher (ablation)VeloxSeg · AutoPET-IIDice (%): 59.71 -> 62.51Improved
add reconstruction texture teacher without Gram supervision (ablation)VeloxSeg · AutoPET-IIDice (%): 61.43 -> 59.64Hurt
use l1, Affinity or shared-ROI transfer loss instead of SDKT (ablation)VeloxSeg · AutoPET-IIDice (%): 59.71 -> 1.67 (l1), 41.44 (Affinity), 57.15 (Shared ROI)Hurt
add Transformer (PWA) attention encoder to JLC convolution (ablation)VeloxSeg · AutoPET-IIDice (%): 55.84 -> 61.03 (with depth 1)Improved
increase attention depth from 1 to 2 per stage (ablation)VeloxSeg · AutoPET-IIDice (%): 61.03 -> 59.56Hurt
unify upsampling strategy (ablation)VeloxSeg · AutoPET-IIGFLOPs and GPU throughput: 2.84 G -> 1.79 G; 336.94 -> 599.06 patches/sImproved
add modal interaction into PWA (ablation)VeloxSeg · AutoPET-II multimodal inputDice (%): +5.75%Improved
use JL-guided group sizes instead of depth-wise convolution (ablation)pure convolution network · Hecktor2022 and BraTS2021Dice (%): +6.25% Hecktor2022; +1.16% BraTS2021Improved
raise convolution group size from 1 to 4,8,8,16 (JL-guided) (ablation)convolution encoder · AutoPET-IIDice (%): 53.65 -> 55.84Improved
larger group size 16,32,64,128 versus 4,8,8,16 (ablation)convolution encoder · AutoPET-IIDice (%): 55.84 -> 56.20 with Params 1.18M -> 4.76MNo clear effect
replace l2 pruning of full convolution with JLC (ablation)convolution network · BraTS2021 to BraTS2016 TCIADice (%): 62.00 -> 79.34Improved
widen convolution channels from 16-128 to 32-256 (ablation)convolution encoder · AutoPET-IIDice (%): 50.10 -> 48.96Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy