AI Paper Atlas

Research map / Detection and segmentation / CNN features

JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method

Vishwanath A. Sindagi, Rajeev Yasarla, Vishal M. Patel

TPAMI 2020 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 297 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 residual learning (ablation)VGG16 base network · JHU-CROWD++ valMAE: 81.1 -> 77.5 (MSE 300.5 -> 290.6)Improved
add confidence estimation blocks without uncertainty (lambda_c=0) (ablation)Base + R (VGG16) · JHU-CROWD++ valMAE: 77.5 -> 77.1No clear effect
add uncertainty guidance (lambda_c=1) to residual blocks (ablation)Base + R (VGG16) · JHU-CROWD++ valMAE: 77.1 -> 74.1 (MSE 290.5 -> 275.5)Improved
add class-conditioning conv block without image-level loss (lambda_w=0) (ablation)Base + R + UREB (VGG16) · JHU-CROWD++ valMAE: 74.1 -> 74.6No clear effect
add image-level classification loss (lambda_w=0.01) to class-conditioning (ablation)Base + R + UREB-C (VGG16) · JHU-CROWD++ valMAE: 74.6 -> 67.9 (MSE 274.1 -> 262.1)Improved
add residual learning (ablation)Res101 base network · JHU-CROWD++ valMAE: 72.1 -> 68.5Improved
add uncertainty guidance (lambda_c=1) to residual blocks (ablation)Base + R (Res101) · JHU-CROWD++ valMAE: 68.2 -> 62.5Improved
add class-conditioning with image-level loss (lambda_w=0.01) (ablation)Base + R + UREB (Res101) · JHU-CROWD++ valMAE: 62.5 -> 57.6 (MSE 258.1 -> 244.4)Improved
use weather labels with multi-task learning only (ablation)CG-DRCN · JHU-CROWD++ weather valMAE: 78.4 -> 74.4 (MSE 170.5 -> 140.1)Improved
add conditioning of residual estimation on weather labels over multi-task learning (ablation)CG-DRCN · JHU-CROWD++ weather valMAE: 74.4 -> 63.6 (MSE 140.1 -> 116.6)Improved
add residual estimation branches at multiple scales (Y6 only to Y6+Y5+Y4+Y3) (ablation)VGG16 · JHU-CROWD++ valMAE: 81.1 -> 67.9Improved
add residual estimation branches at multiple scales (Y6 only to Y6+Y5+Y4+Y3) (ablation)Res101 · JHU-CROWD++ valMAE: 72.1 -> 57.6Improved

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