AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Coreset-Based Neural Network Compression

Abhimanyu Dubey, Moitreya Chatterjee, Narendra Ahuja

ECCV 2018 · Architectures and efficiency › CNN design · approach: CNN filter pruning · 72 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 activation-based pruning (AP) to Coreset-S (ablation)Coreset-S · AlexNet ImageNetcompression ratio: 10.5 -> 19.1Improved
add activation-based pruning (AP) to Coreset-S (ablation)Coreset-S · AlexNet ImageNettop-1 accuracy (%): 56.78 -> 56.38Hurt
add activation-based pruning (AP) to Coreset-K (ablation)Coreset-K · AlexNet ImageNetcompression ratio: 6.7 -> 15.2Improved
add activation-based pruning (AP) to Coreset-A (ablation)Coreset-A · AlexNet ImageNetcompression ratio: 12.3 -> 16.5Improved
add activation-based pruning (AP) to Coreset-S (ablation)Coreset-S · VGGNet-16 ImageNetcompression ratio: 13.9 -> 17Improved
add activation-based pruning (AP) to Coreset-S (ablation)Coreset-S · SqueezeNet ImageNetcompression ratio: 1.9 -> 2.1Improved
couple coreset compression with Deep CompressionAP+Coreset-S · VGGNet-16 ImageNetcompression ratio: 17 -> 233Improved
couple coreset compression with Deep CompressionAP+Coreset-A · AlexNet ImageNetcompression ratio: 16.5 -> 55Improved
use activation-based pruning instead of weight-based pruning (ablation)AP · AlexNet ImageNetaccuracy vs compressionImproved
use AP+Coreset-S instead of SVD or pruning when fine-tuning on CUB-2011VGG-16 compressed · CUB-2011top-1 accuracy (%): 57.45 -> 70.66Improved
use AP+Coreset-S instead of pruning when fine-tuning on Stanford-DogsVGG-16 compressed · Stanford-Dogstop-1 accuracy (%): 43.28 -> 55.91Improved
replace retraining-based Dynamic Net Surgery with coresetscompression pipeline · AlexNet ImageNettraining epochs (time units): 140 -> 28Improved

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