AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization

Juncheng Wang, Lei Shang, Ziqi Liu, Wang Lu, Xixu Hu, Zhe Hu, Jindong Wang, Shujun Wang

IJCV 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 0 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 SemanticHook (ablation)ERM · ScaleBench avgF1: 77.47 -> 78.60Improved
add ScaledLoss on top of SemanticHook (ablation)Catto · ScaleBench avgF1: 78.60 -> 79.27Improved
add S2InvLoss on top of SemanticHook (ablation)Catto · ScaleBench avgF1: 78.60 -> 78.63No clear effect
add S2InvLoss and ScaledLoss together (ablation)Catto with SemanticHook · ScaleBench avgF1: 78.60 -> 79.69Improved
use Gaussian perturbation rather than interpolation (scale) perturbation (ablation)SemanticHook · ScaleBench avgF1: 70.90 -> 78.60Improved
use ColorJitter rather than Gaussian perturbation (ablation)SemanticHook · ScaleBench avgF1: 78.60 vs 78.50No clear effect
enhance hooked semantic feature rather than global feature (ablation)Catto · ScaleBench avgF1: 69.13 -> 78.60Improved
add annealing of gamma (ablation)Catto · ScaleBench avgF1: 73.03 -> 78.60Improved
random interpolation augmentation (RA) in training (ablation)Big-source model · Big->smaller domains avgF1: 56.14 -> 57.96Mixed
inference-time interpolation (IA) (ablation)Big-source model · Big->smaller domains avgF1: 56.14 -> 53.01Hurt
add domain B to training for target S (ablation)multi-source training · ScaleBench target SmallF1: 77.92 -> 77.94No clear effect
use 30% of InD data instead of full (ablation)crowd locator · InD scale splitF1No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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