AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

SemifreddoNets: Partially Frozen Neural Networks for Efficient Computer Vision Systems

Leo F Isikdogan, Bhavin V Nayak, Chyuan-Tyng Wu, Joao Peralta Moreira, Sushma Rao, Gilad Michael

ECCV 2020 · Architectures and efficiency › RNNs and normalization · approach: Efficient network compression and training · 14 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
freeze a larger portion of backbone weights (0%, 50%, 75%, 100%) (ablation)2x-wide ImageNet-pretrained backbone · Cityscapes semantic segmentationpixelwise accuracyHurt
repeat the last Semifreddo blocks twice (ablation)SemifreddoNet · face identificationaccuracy: 88% -> 96%Improved
repeat the blocks further (ablation)SemifreddoNet · face identificationaccuracy: up to 2%No clear effect
add cross-core channel shuffle between the two trainable cores (ablation)SemifreddoNet · classification and face tasksperformanceImproved
keep the first pointwise convolution in ShuffleNetV2 blocks (instead of dropping it) (ablation)SemifreddoNet · face identificationaccuracyNo clear effect
keep the first pointwise convolution in ShuffleNetV2 blocks (instead of dropping it) (ablation)SemifreddoNet · ImageNet classificationtop-5 accuracy: 2% absoluteImproved
fine-tune batch norm parameters in the frozen core (ablation)SemifreddoNet · face identificationaccuracy: 2% absoluteImproved

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