AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Search

Yibo Hu, Xiang Wu, Ran He

ECCV 2020 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 54 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 random sampling for a second path (bi-sampling) in addition to Gumbel (ablation)TF-NAS · ImageNet (15ms target, second-path sampling ablation)top-1 accuracy: 75.8 -> 76.3Improved
add a second Gumbel-sampled path (ablation)TF-NAS · ImageNet (15ms target, second-path sampling ablation)top-1 accuracy: 75.8 -> 75.7Hurt
add a second path chosen by max architecture parameter (ablation)TF-NAS · ImageNet (15ms target, second-path sampling ablation)top-1 accuracy: 75.8 -> 75.5Hurt
replace skip-as-candidate with sink-connecting depth search (ablation)TF-NAS · ImageNet (15ms target, depth-level search space)top-1 accuracy: 75.6 -> 76.3Improved
take skip out of the candidate set (mutual exclusion) (ablation)TF-NAS · ImageNet (15ms target, depth-level search space)top-1 accuracy: 75.6 -> 76.1Improved
eliminate architecture redundancy via sink-connecting (ablation)TF-NAS · ImageNet (15ms target, depth-level search space)top-1 accuracy: 76.1 -> 76.3Improved
add elasticity-scaling to the C1 latency objective (ablation)C1 objective · ImageNet (15ms target, latency objective)top-1 accuracy: 75.6 -> 75.9Improved
add elasticity-scaling to the C2 latency objective (ablation)C2 objective · ImageNet (15ms target, latency objective)top-1 accuracy: 76.2 -> 76.1No clear effect
add elasticity-scaling to the proposed target-latency objective (ablation)TF-NAS · ImageNet (15ms target, latency objective)top-1 accuracy: 76.3 -> 76.3No clear effect
use the proposed target-latency objective instead of C1 (no elasticity-scaling) (ablation)latency objective · ImageNet (15ms target, latency objective)top-1 accuracy: 75.6 -> 76.3Improved
set lambda to 0.1 instead of 0.01 (ablation)TF-NAS · ImageNet (15ms target, lambda sweep)top-1 accuracy: 75.7 -> 76.3Improved
add SE module to candidate operations (TF-NAS-A) (ablation)TF-NAS-A · ImageNet (mobile setting)top-1 accuracy: 76.5 -> 76.9Improved

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