AI Paper Atlas

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

Simulating Content Consistent Vehicle Datasets with Attribute Descent

Yue Yao, Liang Zheng, Xiaodong Yang, Milind Naphade, Tom Gedeon

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 150 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 SPGAN style domain adaptation to synthetic training data (ablation)Attribute descent synthetic data · VehicleIDmAP: 24.36 -> 35.33Improved
add SPGAN style domain adaptation to synthetic training data (ablation)Attribute descent synthetic data · VeRi-776mAP: 12.35 -> 21.29Improved
add second-stage finetuning on real data only (two-stage training) (ablation)Joint training with attribute descent · VehicleIDmAP: 77.54 -> 81.35Improved
add second-stage finetuning on real data only (two-stage training) (ablation)Joint training with attribute descent · VeRi-776mAP: 69.39 -> 70.62Improved
add second-stage finetuning on real data only (two-stage training) (ablation)Joint training with attribute descent · CityFlowmAP: 33.54 -> 37.16Improved
replace random attributes with attribute descent for synthetic-only trainingVehicleX synthetic data · VehicleID (Large)mAP: 22.00 -> 35.33Improved
replace random attributes with attribute descent for synthetic-only trainingVehicleX synthetic data · VeRi-776Rank-1: +7.69%Improved
replace random attributes with attribute descent in joint trainingIDE joint training · VeRi-776mAP: 69.28 -> 70.62Improved
replace random attributes with attribute descent in joint trainingIDE+Tri joint training · CityFlowmAP: 35.96 -> 37.16Improved
add synthetic data with attribute descent to real training dataIDE · VehicleID (Large)mAP: 78.51 -> 81.35Improved
replace random search with attribute descent for attribute optimization (ablation)VehicleX attribute search · VehicleID (Large, synthetic only)mAP: 26.35 -> 35.33Improved
replace LTS (FID-based) with attribute descent for attribute optimization (ablation)VehicleX attribute search · VehicleID (Large, synthetic only)mAP: 32.21 -> 35.33Improved

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