AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Automatic Channel Pruning by Searching with Structure Embedding for Hash Network

Zifan Liu, Yuan Cao, Yifan Sun, Yanwei Yu, Heng Qi

AAAI 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 0 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 unsupervised contrastive learning instead of supervised mAP regression for GCN encoder (ablation)ACP-SSE · CIFAR-10 DCHmAP@all: 0.7623 -> 0.8215Improved
use unsupervised contrastive learning instead of supervised mAP regression for GCN encoder (ablation)ACP-SSE · CIFAR-10 DTSHmAP@all: 0.7832 -> 0.8387Improved
use unsupervised contrastive learning instead of supervised mAP regression for GCN encoder (ablation)ACP-SSE · CIFAR-10 CSQmAP@all: 0.8041 -> 0.8521Improved
add top-k refinement (fine-tune several candidates) (ablation)ACP-SSE · CIFAR-10 DCHmAP@all: 0.7748 -> 0.8215Improved
add top-k refinement (fine-tune several candidates) (ablation)ACP-SSE · CIFAR-10 DTSHmAP@all: 0.7887 -> 0.8387Improved
add top-k refinement (fine-tune several candidates) (ablation)ACP-SSE · CIFAR-10 CSQmAP@all: 0.8175 -> 0.8521Improved
increase k from 1 to 10 (m=50) (ablation)ACP-SSE CSQ ResNet-50 · CIFAR-10mAP: 0.824 -> 0.852Improved
increase candidate pool m beyond 50 (ablation)ACP-SSE CSQ ResNet-50 · CIFAR-10mAP: 0.848 -> 0.852No clear effect
prune with ACP-SSE vs ABCPrunerDTSH ResNet-50 · CIFAR-10mAP@all: 0.8394 -> 0.8387Hurt
prune with ACP-SSE vs AutoSculptDCH ResNet-50 · CIFAR-10mAP@all: 0.8164 -> 0.8215Improved
prune with ACP-SSE vs ABCPrunerDCH ResNet-50 · ImageNet100mAP@all: 0.6433 -> 0.6608Improved

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