AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Influence Function Based Second-Order Channel Pruning: Evaluating True Loss Changes for Pruning is Possible Without Retraining

Hongrong Cheng, Miao Zhang, Qinfeng Shi

TPAMI 2024 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 11 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
replace GFP criterion with IFSO influence-function second-order criterionGFP · CIFAR-10 VGG-16 (40% FLOPs)Top-1 accuracy: 93.72 -> 94.04Improved
replace GFP criterion with IFSOGFP · CIFAR-10 ResNet-32 (50% FLOPs)Top-1 accuracy: 92.64 -> 93.00Improved
replace GFP criterion with IFSOGFP · CIFAR-100 ResNet-56 (50% FLOPs)Top-1 accuracy: 70.17 -> 70.55Improved
replace GFP criterion with IFSOGFP · COCO 2017 RetinaNet (60% FLOPs)mAP: 35.30 -> 35.70Improved
use IFSO on ImageNet ResNet-50 at 40% FLOPs vs SFPSFP · ImageNet ResNet-50 (40% FLOPs)Top-1 accuracy: 74.61 -> 75.70Improved
replace layer-wise normalization of channel scores with IFSO scoring (ablation)Norm-40 · CIFAR-10 ResNet-32 (40% FLOPs)Top-1 accuracy: 93.11 -> 93.23Improved
replace raw scores with IFSO scoring (ablation)Raw-40 · CIFAR-10 ResNet-32 (40% FLOPs)Top-1 accuracy: 92.83 -> 93.23Improved
normalization policies on ResNet-56 at 50% FLOPs (ablation)Raw-50 · CIFAR-10 ResNet-56 (50% FLOPs)Top-1 accuracy: 93.65 -> 93.72Mixed
use identity instead of Neumann-1 approximation of inverse Hessian (ablation)Neumann-1-40 · CIFAR-10 ResNet-32 (40% FLOPs)Top-1 accuracy: 93.14 -> 93.23Improved
use identity instead of Neumann-2 approximation (ablation)Neumann-2-50 · CIFAR-10 ResNet-32 (50% FLOPs)Top-1 accuracy: 92.67 -> 93.00Improved
accumulate channel scores k times instead of using the k-th scores (ablation)IFSO · CIFAR-10 ResNet-32 (50% FLOPs)Top-1 accuracyImproved
use more batches of proxy dataset (ablation)IFSO · CIFAR-10Top-1 accuracyNo clear effect

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