AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization

Haibao Yu, Qi Han, Jianbo Li, Jianping Shi, Guangliang Cheng, Bin Fan

ECCV 2020 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search · 55 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 BP-NAS instead of HAWQ at a 4-bit budgetHAWQ · CIFAR-10 (ResNet20)Top-1 accuracy: 92.22 -> 92.30Improved
use BP-NAS instead of HAWQ at a 4-bit budgetHAWQ · CIFAR-10 (ResNet20)BOPs compression ratio: 64.49 -> 81.53Improved
use BP-NAS (3-bit budget) instead of fixed 3-bit PACTPACT · CIFAR-10 (ResNet20)Top-1 accuracy: 91.10 -> 92.04Improved
use BP-NAS (3-bit budget) instead of fixed 3-bit LQ-NetsLQ-Nets · CIFAR-10 (ResNet20)Top-1 accuracy: 91.60 -> 92.04Improved
use mixed precision from BP-NAS instead of fixed (4,4)-bitBaseline (4,4)-bit · ImageNet (ResNet50)Top-1 accuracy: 76.02 -> 76.67Improved
use BP-NAS (3-bit budget) instead of fixed 3-bit PACTPACT · ImageNet (ResNet50)Top-1 accuracy: 75.30 -> 75.71Improved
use BP-NAS instead of HAWQHAWQ · ImageNet (ResNet50)Top-1 accuracy: 75.30 -> 75.71Improved
use mixed 4-bit BP-NAS instead of uniform 4-bitBaseline 4-bit · COCO (Faster R-CNN ResNet50)AP: 0.343 -> 0.358Improved
use own 4-bit baseline instead of FQNFQN · COCO (Faster R-CNN ResNet50)AP: 0.331 -> 0.343Improved
add barrier penalty regularizer to the search (ablation)BP-NAS · CIFAR-10 (ResNet20)Top-1 accuracy: 92.6 -> 92.04Mixed
add distribution reshaping (uniformization) in training (ablation)mixed-precision ResNet20 · CIFAR-10 (ResNet20)Top-1 accuracy: 60 -> 89Improved
add Prob-1 regularizer to the supernet (ablation)BP-NAS · CIFAR-10 (ResNet20)importance factor selectivityImproved

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