AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Performance-Aware Approximation of Global Channel Pruning for Multitask CNNs

Hancheng Ye, Bo Zhang, Tao Chen, Jiayuan Fan, Bin Wang

TPAMI 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 45 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
use sequentially greedy pruning instead of layer-wise pruning (ablation)PAGCP SSD300 · PASCAL VOCmAP (%): 73.2 -> 75.6Improved
use sequentially greedy pruning instead of one-shot global pruning (ablation)PAGCP SSD300 · PASCAL VOCmAP (%): 74.3 -> 75.6Improved
use sequentially greedy pruning instead of group pruning (ablation)PAGCP SSD300 · PASCAL VOCmAP (%): 75.2 -> 75.6Improved
use max over tasks instead of min in oracle criterion (ablation)PAGCP SSD300 · PASCAL VOCmAP (%): 49.0 -> 75.9Improved
use max instead of l1 sum in oracle criterion (ablation)PAGCP SSD300 · PASCAL VOCmAP (%): 75.4 -> 75.9Improved
use max instead of l2 in oracle criterion (ablation)PAGCP SSD300 · PASCAL VOCmAP (%): 75.6 -> 75.9Improved
include all four subtasks in the performance-aware criterion instead of initial segmentation only (ablation)PAGCP MTI-Net · NYUD-v2mIoU (%): 35.9 -> 37.4Improved
run more pruning iterations on SSD300 (ablation)PAGCP · PASCAL VOCmAP (%): 76.2 -> 75.6Hurt
prune with PAGCP instead of scaling down to YOLOv5sYOLOv5m · PASCAL VOCmAP (%): 79.5 -> 81.7Improved

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