AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Partial Forward Blocking: A Novel Data Pruning Paradigm for Lossless Training Acceleration

Dongyue Wu, Zilin Guo, Jialong Zuo, Nong Sang, Changxin Gao

ICCV 2025 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 4 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 adaptive centroid weight w_j in KDE (ablation)PFB · CIFAR-100 (70% pruned)top-1 accuracy: 77.4 -> 77.9Improved
add adaptive centroid weight w_j in KDE (ablation)PFB · CIFAR-100 (30% pruned)top-1 accuracy: 78.9 -> 79.1Improved
add adaptive centroid weight w_j in KDE (ablation)PFB · CIFAR-100 (50% pruned)top-1 accuracy: 78.4 -> 78.8Improved
use Silverman bandwidth instead of identity matrix (ablation)PFB · CIFAR-100 (70% pruned)top-1 accuracy: 75.1 -> 77.9Improved
use Silverman bandwidth instead of identity matrix (ablation)PFB · CIFAR-100 (30% pruned)top-1 accuracy: 77.4 -> 79.1Improved
use Silverman bandwidth instead of identity matrix (ablation)PFB · CIFAR-100 (50% pruned)top-1 accuracy: 76.5 -> 78.8Improved
use Silverman instead of Scott bandwidth rule (ablation)PFB · CIFAR-100 (30% pruned)top-1 accuracy: 79.0 -> 79.1No clear effect
increase random-term upper bound b to 10 (ablation)PFB · CIFAR-100top-1 accuracyHurt
vary random-term upper bound b within [0.001, 1] (ablation)PFB · CIFAR-100top-1 accuracyNo clear effect
apply blocking at stem layers (stage-0) instead of stage-1 (ablation)PFB · ImageNet-1ktop-1 accuracyHurt
vary number of centroids N_C and feature dimension D within normal range (ablation)PFB · CIFAR-100top-1 accuracyNo clear effect
vary batch size (ablation)PFB · ImageNet-1ktop-1 accuracyNo 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