AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Batch Pruning by Activation Stability

Md Mustakin Alam, Shaker Islam, Aminul Islam

ICLR 2026 · Architectures and efficiency › CNN design · approach: Theory of convolutional inductive bias

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 Batch Normalization to ResNet-18 under B-PAS (ablation)B-PAS · CIFAR-10 (ResNet-18)accuracy: 89.87 -> 95.60Improved
add batch-level instead of sample-level pruning (ablation)B-PAS · ImageNet-1K (ResNet-50)top-1 accuracy: 70.87 -> 78.43Improved
train 200 epochs instead of 90 epochs (ablation)B-PAS · ImageNet-1K (ResNet-50)DSI (%): 12 -> 47Improved
learning rate 0.1 instead of 0.01 (ablation)B-PAS · ImageNet-1K (ResNet-50)top-1 accuracy: 74.29 -> 78.43Improved
use mean std instead of entropy to quantify stability (ablation)B-PAS · CIFAR-10 (ResNet-18)accuracy: 89.64 -> 95.60Improved
use mean std instead of max std to quantify stability (ablation)B-PAS · CIFAR-10 (ResNet-18)DSI (%): 13.45 -> 25.06Improved
use Batch Norm instead of Layer Norm (ablation)B-PAS · CIFAR-10 (ResNet-18)accuracy: 93.99 -> 95.60Improved
increase batch size from 32 to 128 (ablation)B-PAS · CIFAR-10 (ResNet-18)DSI (%): 20.25 -> 25.06Improved
swap B-PAS for random pruning of the same number of batches (ablation)ResNet-18 · CIFAR-100 (ResNet-18)accuracy: 78.20 -> 75.36Hurt
add B-PAS to ResNet-50 full-data trainingResNet-50 · ImageNet-1K (ResNet-50)top-1 accuracy: 78.07 -> 78.43Improved
use more aggressive delta schedule (5x10^-5 to 5x10^-4) in B-PAS (ablation)B-PAS · ImageNet-1K (ResNet-50)top-1 accuracy: 78.07 -> 76.10Hurt
add B-PAS to CvT-13 trainingCvT-13 · ImageNet-1K (CvT)top-1 accuracy: 79.65 -> 79.6No clear effect

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