AI Paper Atlas

Research map / Architectures and efficiency / CNN design

LST-Net: Learning a Convolutional Neural Network with a Learnable Sparse Transform

Lida Li, Kun Wang, Shuai Li, Xiangchu Feng, Lei Zhang

ECCV 2020 · Architectures and efficiency › CNN design · approach: CNN filter pruning · 32 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
initialize spatial and channel transforms with 2D-DCT instead of random (ablation)LST-Net · CIFAR-100top-1 error: 31.12 -> 28.21 (20 layers); 28.94 -> 21.94 (164 layers)Improved
use soft thresholding with tau=1e-4 instead of tau=0 (plain ReLU) (ablation)LST-Net-20 · CIFAR-100top-1 error: 28.92 -> 28.21Improved
use LST-II bottleneck instead of LST-I (ablation)LST-Net · CIFAR-100top-1 error: 27.64 -> 28.21 (20 layers, LST-II worse); 23.15 -> 21.94 (164 layers)Improved
use ReLU-ST instead of ReLU (ablation)LST-Net · CIFAR-100top-1 error: 28.92 -> 28.21 (20 layers); 22.86 -> 21.94 (164 layers)Improved
use ReLU-ST instead of ELU (ablation)LST-Net-164 · CIFAR-100top-1 error: 29.94 -> 21.94Improved
replace Conv2d bottleneck with LST (ResNet-110)ResNet-110 · CIFAR-100top-1 error: 25.2 -> 22.7Improved
replace Conv2d bottleneck with LST (ResNet-18)ResNet-18 · ImageNettop-1 error: 30.24 -> 26.55Improved
add soft thresholding to LST-Net activation (ablation)LST-Net-18 · ImageNet-CmCE: 80.34 -> 79.89Improved
add soft thresholding to LST-Net activation (ablation)LST-Net-50 · ImageNet-CmCE: 70.85 -> 70.54Improved
replace Conv2d with LST vs adding SE/CBAM attentionResNet-18 · ImageNet-CmCE: 83.97 -> 79.89Improved
increase WRN-28 width multiplier from 10 to 12WRN · CIFAR-10error rate: 4.17 -> 4.33Mixed
vary tau across 1e-1 to 1e-6 (ablation)LST-Net-20 · CIFAR-100top-1 error: 28.32, 28.28, 28.86, 28.21, 28.43, 28.70Mixed

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