AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Towards Regression-Free Neural Networks for Diverse Compute Platforms

Rahul Duggal, Hao Zhou, Shuo Yang, Jun Fang, Yuanjun Xiong, Wei Xia

ECCV 2022 · Learning theory and algorithms › Kernels and regression theory · approach: High-dimensional asymptotic generalization · 2 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
jointly search reference and target with REG-NAS instead of independent EffNet trainingEfficientNet-B1 · ImageNet val (MobileNet-V3 space)NFR (%): 4.25 -> 2.16Improved
REG-NAS instead of focal distillation (EffNet+FD)EffNet+FD · ImageNet val (MobileNet-V3 space)NFR (%): 3.25 -> 2.16Improved
REG-NAS instead of focal distillation (RN101+FD)RN101+FD · ImageNet val (ResNet space)NFR (%): 3.06 -> 1.57Improved
add architecture constraint (CAS) to reward R2 (ablation)MB-R2-300 · ImageNet val (MobileNet-V3 space)NFR (%): 2.25 -> 2.16Improved
add architecture constraint (CAS) to reward R2 (ablation)RN-R2-3000 · ImageNet val (ResNet space)NFR (%): 1.76 -> 1.57Improved
use reward R2 (accuracy and NFR) instead of R0 (accuracy only) (ablation)MB-R0-300 · ImageNet val (MobileNet-V3 space)NFR (%): 2.51 -> 2.25Improved
use reward R1 (NFR only) instead of R2 (ablation)MB-R2-300 · ImageNet val (MobileNet-V3 space)Top-1 accuracy (%): 76.90 -> 76.20Hurt
fine-tune with CE (ablation)MB-R0-300 · ImageNet val (MobileNet-V3 space)NFR (%): 2.51 -> 2.53No clear effect
fine-tune with CE (ablation)RN-R0-3000 · ImageNet val (ResNet space)NFR (%): 2.04 -> 2.47Hurt
fine-tune with FD loss (ablation)RN-(R2+CAS)-3000 · ImageNet val (ResNet space)NFR (%): 1.57 -> 0.96Improved
fine-tune with FD loss (ablation)MB-(R2+CAS)-300 · ImageNet val (MobileNet-V3 space)NFR (%): 2.16 -> 2.12Improved
search small to large instead of large to small (ablation)REG-NAS · ImageNet val (MobileNet-V3 space)NFRImproved

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