AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

NAS-Count: Counting-by-Density with Neural Architecture Search

Yutao Hu ¹, Xiaolong Jiang ², Xuhui Liu, Baochang Zhang, Jungong Han, Xianbin Cao ², David Doermann

ECCV 2020 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 119 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 searched AMSNet encoder instead of baseline encoder (ablation)baseline encoder + decoder · ShanghaiTech Part_A (ablation)MAE: 69.1 -> 60.3Improved
use searched AMSNet encoder instead of baseline encoder (ablation)baseline encoder + decoder · ShanghaiTech Part_A (ablation)PSNR: 23.54 -> 25.82Improved
use searched AMSNet decoder instead of baseline decoder (ablation)baseline encoder + decoder · ShanghaiTech Part_A (ablation)MAE: 69.1 -> 62.4Improved
use searched AMSNet decoder instead of baseline decoder (ablation)baseline encoder + decoder · ShanghaiTech Part_A (ablation)PSNR: 23.54 -> 24.75Improved
search encoder on counting instead of using classification-searched backbone (ablation)classification encoder · ShanghaiTech Part_A (ablation)MAE: 67.8 -> 60.3Improved
search encoder on counting instead of using classification-searched backbone (ablation)classification encoder · ShanghaiTech Part_A (ablation)PSNR: 23.67 -> 25.82Improved
add hand-designed pyramid SAL loss over MSE (ablation)AMSNet · ShanghaiTech Part_A (ablation)MAE: 58.5 -> 57.6Improved
replace SAL with searched SPPLoss (ablation)AMSNet · ShanghaiTech Part_A (ablation)MAE: 57.6 -> 56.7Improved
add searched SPPLoss over MSE (ablation)AMSNet · ShanghaiTech Part_A (ablation)PSNR: 26.17 -> 27.03Improved
reduce output channels C from 512 to 256 (AMSNet_light) (ablation)AMSNet · ShanghaiTech Part_AMAE: 56.7 -> 61.3Hurt
reduce output channels C from 512 to 256 (AMSNet_light) (ablation)AMSNet · ShanghaiTech Part_Amodel size: 3.79MB -> 1.51MBImproved

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