AI Paper Atlas

Research map / Image generation / Editing and style transfer

AugGAN: Cross Domain Adaptation with GAN-based Data Augmentation

Sheng-Wei Huang, Che-Tsung Lin, Shu-Ping Chen, Yen-Yi Wu, Po-Hao Hsu, Shang-Hong Lai

ECCV 2018 · Image generation › Editing and style transfer · approach: Image-to-image translation · 283 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 segmentation parsing to the inverse cycle as well as the forward cycle (ablation)AugGAN · SYNTHIA day-train, SYNTHIA night-test (Faster RCNN)vehicle detection AP (%): 68.7 -> 72.2Improved
add segmentation parsing to the inverse cycle as well as the forward cycle (ablation)AugGAN · SYNTHIA day-train, SYNTHIA night-test (YOLO)vehicle detection AP (%): 38.1 -> 39.0Improved
add soft weight sharing (lambda_w=0.02) in the decoder instead of hard sharing (ablation)AugGAN · SYNTHIA day-train, SYNTHIA night-test (Faster RCNN)vehicle detection AP (%): 57.2 -> 68.7Improved
share decoder weights between generator and parsing net (hard) on top of encoder hard-sharing (ablation)AugGAN · SYNTHIA day-train, SYNTHIA night-test (Faster RCNN)vehicle detection AP (%): 39.9 -> 57.2Improved
use AugGAN instead of CycleGAN for translated training dataFaster RCNN · SYNTHIA day-train, SYNTHIA night-testvehicle detection AP (%): 65.9 -> 72.2Improved
use AugGAN instead of UNIT for translated training dataYOLO · KITTI-D2N (GTA GAN) train, ITRI-Night testvehicle detection AP (%): 20.5 -> 46.0Improved
use AugGAN instead of CycleGAN on GTA-trained translationFaster-RCNN · GTA day-to-night train, GTA night-testvehicle detection AP (%): 54.4 -> 67.4Improved
use AugGAN instead of CycleGAN on ITRI-Day with GTA-trained GANFaster RCNN · ITRI-Day D2N (GTA GAN) train, ITRI-Night testvehicle detection AP (%): 86.2 -> 86.1No clear effect
use AugGAN instead of CycleGAN on ITRI-Day with SYNTHIA-trained GANFaster RCNN · ITRI-Day D2N (SYNTHIA GAN) train, ITRI-Night testvehicle detection AP (%): 72.4 -> 81.2Improved
use AugGAN instead of CycleGAN on ITRI-Day with GTA-trained GANYOLO · ITRI-Day D2N (GTA GAN) train, ITRI-Night testvehicle detection AP (%): 37.9 -> 44.1Improved

Later papers that compared with this method

1 later accepted paper reports AugGAN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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