Unsupervised Adaptation of Semantic Segmentation Models without Source Data

Autor: Paul, Sujoy, Khurana, Ansh, Aggarwal, Gaurav

We consider the novel problem of unsupervised domain adaptation of source models, without access to the source data for semantic segmentation. Unsupervised domain adaptation aims to adapt a model learned on the labeled source data, to a new unlabeled

Externí odkaz: http://arxiv.org/abs/2112.02359

Multi-Stage Fusion for One-Click Segmentation

Autor: Majumder, Soumajit, Khurana, Ansh, Rai, Abhinav, Yao, Angela

Segmenting objects of interest in an image is an essential building block of applications such as photo-editing and image analysis. Under interactive settings, one should achieve good segmentations while minimizing user input. Current deep learning-b

Externí odkaz: http://arxiv.org/abs/2010.09672

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Retrograde NaviAid Enteroscopy-Assisted Resection of Distal Small Bowel Hamartomatous Polyps.

Autor: Sinha A; Division of Gastroenterology and Nutrition, Geisinger Health System, Danville, USA., Johal AS; Division of Gastroenterology and Nutrition, Geisinger Health System, Danville, USA., Khurana A; Division of Gastroenterology and Nutrition, Geisinger Health System, Danville, USA., Basi P; Department of Gastroenterology, UPMC Susquehanna Health, Williamsport, USA., Khara HS; Division of Gastroenterology and Nutrition, Geisinger Health System, Danville, USA.

Publikováno v: Cureus [Cureus] 2020 Dec 07; Vol. 12 (12), pp. e11962. Date of Electronic Publication: 2020 Dec 07.