AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Completely Self-Supervised Crowd Counting via Distribution Matching

Deepak Babu Sam, Abhinav Agarwalla, Jimmy Joseph, Vishwanath A. Sindagi, R. Venkatesh Babu, Vishal M. Patel

ECCV 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 30 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 Stage 1 rotation self-supervised pretraining before Sinkhorn training (ablation)CSS-CCNN · ShanghaiTech Part A (single run)MAE: 257.5 -> 197.3Improved
use rotation pretext instead of colorization (ablation)CSS-CCNN · ShanghaiTech Part A (single run)MAE: 242.5 -> 197.3Improved
use rotation self-supervision instead of ImageNet weights for the FEN (ablation)CSS-CCNN · ShanghaiTech Part A (single run)MAE: 257.8 -> 197.3Improved
use VGG-style FEN instead of ResNet blocks (ablation)CSS-CCNN · ShanghaiTech Part A (single run)MAE: 244.8 -> 197.3Improved
use truncated power-law prior instead of uniform prior (ablation)CSS-CCNN · ShanghaiTech Part A (single run)MAE: 261.8 -> 197.3Improved
add skip features from the second conv block to the regressor (ablation)CSS-CCNN · ShanghaiTech Part A (single run)MAE: 226.8 -> 197.3Improved
use 4 rotation classes instead of 2 (ablation)CSS-CCNN · ShanghaiTech Part A (single run)MAE: 233.5 -> 197.3Improved
use 8x8 cells instead of 4x4 for count histograms (ablation)CSS-CCNN · ShanghaiTech Part A (single run)MAE: 251.6 -> 197.3Improved
use ground-truth count distribution instead of the parametric prior (ablation)CSS-CCNN · ShanghaiTech Part A (single run)MAE: 197.3 vs 202.7No clear effect
add edge-based pseudo density grouping to Sinkhorn loss (CSS-CCNN++)CSS-CCNN · ShanghaiTech Part AMAE: 207.3 -> 195.6Improved
add edge-based pseudo density grouping to Sinkhorn loss (CSS-CCNN++)CSS-CCNN · UCF-QNRFMAE: 442.4 -> 414.0Improved
add edge-based pseudo density grouping to Sinkhorn loss (CSS-CCNN++)CSS-CCNN · JHU-CROWD++MAE: 243.6 -> 197.9Improved

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