AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Prioritized Subnet Sampling for Resource-Adaptive Supernet Training

Bohong Chen, Mingbao Lin, Rongrong Ji, Liujuan Cao

TPAMI 2023 · Architectures and efficiency › RNNs and normalization · approach: Efficient network compression and training · 5 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 prioritized subnet pools instead of uniform sampling (vs USNet, MobileNet-V1 ~110M FLOPs)USNet · ImageNet valtop-1 accuracy (%): 61.9 -> 67.9Improved
use prioritized subnet sampling instead of MutualNet (MobileNet-V1 ~110M FLOPs)MutualNet · ImageNet valtop-1 accuracy (%): 63.5 -> 67.9Improved
train under multiple constraints (PSS-Net_M) instead of FLOPs onlyPSS-Net · ImageNet val (MobileNet-V1 569M)top-1 accuracy (%): 74.2 -> 74.5No clear effect
add prioritized subnet sampling vs random search at 300M FLOPs (ablation)PSS-Net · ImageNet val (MobileNet-V1)top-1 accuracy (%): 71.2 -> 72.3 (+1.1)Improved
add prioritized subnet sampling vs random search at 400M FLOPs (ablation)PSS-Net · ImageNet val (MobileNet-V1)top-1 accuracy (%): 72.5 -> 72.9 (+0.4)Improved
add prioritized subnet sampling vs random search at 500M FLOPs (ablation)PSS-Net · ImageNet val (MobileNet-V1)top-1 accuracy (%): 73.7 -> 73.8 (+0.1)No clear effect
calibrate top-5 subnets instead of top-1 for BN (ablation)PSS-Net · ImageNet val (MobileNet-V1) 300Mtop-1 accuracy (%): 71.4 -> 72.3 (+0.9)Improved
increase calibrated subnets from top-5 to top-20 (ablation)PSS-Net · ImageNet val (MobileNet-V1) 300Mtop-1 accuracy (%): 72.3 -> 72.4No clear effect
increase pool size M from 10 to 500 (baseline 50) (ablation)PSS-Net · ImageNet val (MobileNet-V1)top-1 accuracy (%): avg boost -0.3 (M=10) vs +0.1 (M=500)Improved
vary p_end (0.1, 0.001) from 0.01 (ablation)PSS-Net · ImageNet val (MobileNet-V1)top-1 accuracy (%): avg boost -0.1 and +0.0No clear effect
vary eta_end (0.1, 0.001) from 0.01 (ablation)PSS-Net · ImageNet val (MobileNet-V1)top-1 accuracy (%): avg boost -0.2 and -0.1No clear effect
use channel divisor 4 instead of 8 / 16 hurts (ablation)PSS-Net · ImageNet val (MobileNet-V1) 300Mtop-1 accuracy (%): divisor 16: 71.2; divisor 8: 72.3; divisor 4: 72.5Improved

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