AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Multicoated Supermasks Enhance Hidden Networks

Yasuyuki Okoshi, Ángel López Garcı́a-Arias, Kazutoshi Hirose, Kota Ando, Kazushi Kawamura, Thiem Van Chu, Masato Motomura, Jaehoon Yu

ICML 2022 · Architectures and efficiency › RNNs and normalization · approach: Efficient network compression and training · 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
Increase number of coats from 1 (Hidden Networks) to 7 with Linear density setting (ablation)ResNet-50 supermask · ImageNetTop-1 Test Acc. (%): overperforms Hidden Networks by 5.65%Improved
Use multiple coats (N>1) instead of a single supermask (ablation)Hidden Networks on CIFAR-10 ResNet-18 · CIFAR-10Top-1 Test Acc. (%)Improved
Linear coat density scheme instead of Uniform (ablation)Multicoated Supermask on CIFAR-10 ResNet-18 · CIFAR-10Top-1 Test Acc. (%)Improved
Shared scores across coats instead of independent scores per mask (ablation)Multicoated Supermask on ResNet-50 · ImageNetTop-1 Test Acc. (%)Improved
Remove weight-initialization advantage: standard Kaiming normal instead of Signed Kaiming Constant as number of coats grows (ablation)Multicoated Supermask on ImageNet ResNet-50 · ImageNetTop-1 Test Acc. (%)No clear effect
Increase total density k1 from ~30% to higher values with multicoating on CIFAR-10 (ablation)Multicoated Supermask ResNet-18 · CIFAR-10Top-1 Test Acc. (%)Mixed
Multicoated Supermask (N=7) vs Hidden Networks at similar model size on ImageNet ResNet-101ResNet-101 multicoated · ImageNetTop-1 Test Acc. (%): 76.46% vs 73.85% for Wide ResNet-50 at similar sizeImproved
Multicoating at 90% sparsity on ResNet-50 (N=7) vs pruning/RigL/MEST baselinesResNet-50 multicoated supermask · ImageNetTop-1 Test Acc. (%): 72.5 vs 75.2-76.1 for baselines at same sparsityHurt

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