AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Stimulative Training++: Go Beyond the Performance Limits of Residual Networks

Peng Ye, Tong He, Shengji Tang, Baopu Li, Tao Chen, Lei Bai, Wanli Ouyang

TPAMI 2025 · Architectures and efficiency › Pruning and efficient tuning · approach: Sparse training from scratch · 9 citations (OpenAlex)

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 stimulative training (subnet sampling + KL) (ablation)ResNet50 common training · ImageNet-1ktop-1 accuracy (%): 76.70 -> 77.56Improved
add KL- loss with 6 sampled subnets (ablation)ResNet50 ST · ImageNet-1ktop-1 accuracy (%): 77.56 -> 78.53Improved
add random smaller subnet inputs (SITrans) (ablation)ResNet50 ST · ImageNet-1ktop-1 accuracy (%): 77.56 -> 78.56Improved
add SITrans to ST with KL- and Snet6 (ablation)ResNet50 ST · ImageNet-1ktop-1 accuracy (%): 78.53 -> 79.83Improved
adjust val resize 240 and train crop 200 (ablation)ResNet50 ST++ · ImageNet-1ktop-1 accuracy (%): 79.83 -> 80.04Improved
add inter-stage sampling rule (InterSSR) (ablation)ResNet50 ST++ · ImageNet-1ktop-1 accuracy (%): 80.04 -> 80.50Improved
add uniform augment and extend to 400 epochs (ablation)ResNet50 ST++ (A1) · ImageNet-1ktop-1 accuracy (%): 80.50 -> 80.97Improved
use larger subnet inputs (up to 272 instead of 224) (ablation)ResNet50 ST · ImageNet-1ktop-1 accuracy (%): 78.562 -> 78.058Hurt
apply jitter and flip transforms to subnet inputs instead of downscaling (ablation)ResNet50 ST · ImageNet-1ktop-1 accuracy (%): 77.564 -> 76.566Hurt
sampling space [1,2,4,1] instead of [3,4,6,3] (ablation)ResNet50 ST++ · ImageNet-1ktop-1 accuracy (%): 80.038 -> 80.496Improved
ordered residual sampling instead of stochastic residual sampling (ablation)MobileNetV3 · CIFAR-100accuracy: +0.58%Improved
finetune with subnet sampling (ST*) instead of plain finetuning of ST++ weightsFaster R-CNN R50-ST · COCO (AdamW)Bbox mAP: 40.0 -> 41.9Improved

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