AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Crowd Counting With Deep Structured Scale Integration Network

Lingbo Liu, Zhilin Qiu, Guanbin Li, Shufan Liu, Wanli Ouyang, Liang Lin

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 292 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
add CRF-based structured feature enhancement (2 iterations) instead of no feature refinement (ablation)DSSINet · ShanghaiTech Part AMAE: 68.85 -> 60.63Improved
use CRF refinement instead of concatenation + 1x1 conv (ablation)DSSINet · ShanghaiTech Part AMAE: 67.11 -> 60.63Improved
increase CRF iterations from 2 to 3 (ablation)DSSINet · ShanghaiTech Part AMAE: 60.63 -> 63.80Hurt
increase CRF iterations from 1 to 2 (ablation)DSSINet · ShanghaiTech Part AMAE: 64.37 -> 60.63Improved
use image pyramid with 3 scales instead of single scale (ablation)DSSINet · ShanghaiTech Part AMAE: 70.94 -> 60.63Improved
add a fourth pyramid scale (0.25) (ablation)DSSINet · ShanghaiTech Part AMAE: 60.63 -> 61.13No clear effect
use DMS-SSIM-5 loss instead of Euclidean loss (ablation)DSSINet · ShanghaiTech Part AMAE: 67.68 -> 60.63Improved
use DMS-SSIM-5 loss instead of plain SSIM loss (ablation)DSSINet · ShanghaiTech Part AMAE: 74.60 -> 60.63Improved
add dilation to multiscale SSIM loss (DMS-SSIM-5 vs MS-SSIM-5) (ablation)DSSINet · ShanghaiTech Part AMAE: 63.51 -> 60.63Improved
add a sixth dilated layer (rate 9) to DMS-SSIM loss (ablation)DSSINet · ShanghaiTech Part AMAE: 60.63 -> 62.60Hurt
increase DMS-SSIM scales from 2 to 5 (ablation)DSSINet · ShanghaiTech Part AMAE: 73.33 -> 60.63Improved

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