AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

SeGAN: Segmenting and Generating the Invisible

Kiana Ehsani, Roozbeh Mottaghi, Ali Farhadi

CVPR 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 181 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 predict the full-object mask and paint its invisible regionsSeGAN · DYCE synthetic test, full-object segmentationIoU: 47.51 -> 68.78Improved
Jointly predict the full-object mask and paint its invisible regionsSeGAN · DYCE synthetic test, invisible-region segmentationIoU: 12.3 -> 15.59Improved
Use SeGAN instead of Pix2Pix for appearance generationDYCE synthetic test · DYCE synthetic testL1 distance: 0.15 -> 0.07Improved
Use SeGAN instead of Pix2Pix for appearance generationDYCE synthetic test · DYCE synthetic testL2 distance: 0.09 -> 0.03Improved
Train on synthetic occlusion data and evaluate on natural imagesSeGAN · PASCAL 3D indoor categories, invisible-region segmentationIoU: 13.9 -> 18.7Improved
Combine natural and synthetic training data instead of using natural data aloneMultipath · PASCAL 3D indoor categories, invisible-region segmentationIoU: 13.9 -> 8.4Hurt
Use groundtruth visible-region masks instead of predicted masksSeGAN · DYCE synthetic test, invisible-region segmentationIoU: 15.59 -> 23.26Improved
Use groundtruth visible-region masks instead of predicted masksSeGAN · DYCE synthetic testL1 distance: 0.07 -> 0.03Improved
Infer object occlusion from predicted invisible-region masks rather than single-image depth estimatesSeGAN · DYCE test occlusion pairsdepth layering accuracy: 60.18 -> 84.04Improved

Later papers that compared with this method

2 later accepted papers report SeGAN as a baseline in their results tables; 2 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