AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networks

Irene Tenison, Soumyajit Chatterjee, Fahim Kawsar, Mohammad Malekzadeh

CVPR 2026 · Architectures and efficiency › RNNs and normalization · approach: Efficient network compression and training · 1 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
select layers with gradient-free Betti-number ranking instead of Fisher Information / other baselinespre-trained DNNs (ImageNet) · 16 model-dataset pairsavg top-1 accuracy (%): 73.75 -> 76.26 (best baseline Last-K vs AdaBet)Improved
AdaBet instead of Fisher Information layer selectionViT · Stanford Dogs / Oxford Pets / CUB / Flowers102top-1 accuracy (%): Stanford Dogs 14.37 -> 85.12; Flowers102 13.10 -> 98.55Improved
AdaBet instead of ElasticTrainerViT · Stanford Dogstop-1 accuracy (%): 87.79 -> 85.12Hurt
AdaBet instead of ElasticTrainerpre-trained DNNs · 16 model-dataset pairstop-1 accuracy (%): ResNet50 CUB 24.37 -> 46.37; ViT CUB 82.93 -> 79.47Mixed
train only ~10% layers selected gradient-free vs full trainingResNet50 · peak memorypeak training memory (MB): 777.12 -> 261.78Improved
AdaBet instead of full trainingViT · peak memorypeak training memory (MB): 386.60 -> 93.64Improved
AdaBet vs Fisher Information for training timeResNet50 / ViT · Oxford-IIIT Petsper-epoch training time: text only, FI shorter than AdaBetHurt
lower layer proportion rho (ablation)AdaBet ResNet50 · Stanford Dogsaccuracy and peak memory: memory drops ~65% at rho=0.1 vs 1.0; accuracy stableImproved
lower channel proportion rho_ch to 0.1 (rho=0.5) (ablation)AdaBet ResNet50 · Oxford-IIIT Petsaccuracy and peak memory: memory drops ~74%; accuracy stableImproved
AdaBet selection step vs ElasticTrainerResNet50 / ViT · Oxford-IIIT Petsselection time: 45% fasterImproved
AdaBet vs full trainingResNet50 / ViT · Oxford-IIIT Petsper-epoch training time: nearly 11% reduction (15% and 7%)Improved

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