AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

SJDL-Vehicle: Semi-supervised Joint Defogging Learning for Foggy Vehicle Re-identification

Wei-Ting Chen, I-Hsiang Chen, Chih-Yuan Yeh, Hao-Hsiang Yang, Jian-Jiun Ding, Sy-Yen Kuo

AAAI 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 17 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
Jointly train the defogging and ReID branches (ablation)ResNet-50 vehicle ReID · FVRID_RealmAP: 76.17 -> 79.47Improved
Add semi-supervised optimization on real-world foggy images (ablation)JDL · FVRID_RealmAP: 79.47 -> 82.70Improved
Add semi-supervised optimization on real-world foggy images (ablation)JDL · FVRID_SynmAP: 83.04 -> 85.36Improved
Add the self-constraint loss LSC (ablation)SJDL-Vehicle · FVRID_RealmAP: 81.50 -> 82.70Improved
Add the self-constraint loss LSC (ablation)SJDL-Vehicle · FVRID_SynmAP: 84.39 -> 85.36Improved
Use Conv_2 for the collective feature sharing module instead of Conv_3 (ablation)SJDL-Vehicle · FVRID_RealmAP: 81.94 -> 82.70Improved
Use Conv_2 for the collective feature sharing module instead of Conv_4 (ablation)SJDL-Vehicle · FVRID_RealmAP: 81.57 -> 82.70Improved
Use Conv_2 for the collective feature sharing module instead of Conv_5 (ablation)SJDL-Vehicle · FVRID_RealmAP: 79.39 -> 82.70Improved
Train the ReID model on foggy data rather than clear dataPVEN · FVRID_RealmAP: 75.36 -> 81.92Improved
Apply two-stage defogging before ReIDPVEN · FVRID_RealmAP: 75.36 -> 78.13Improved
Apply two-stage defogging before ReIDTransReID · FVRID_RealmAP: 64.00 -> 65.30Improved
Apply two-stage defogging before ReIDVOC · FVRID_RealmAP: 57.40 -> 49.20Hurt

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