Synthetic DOmain-Targeted Augmentation (S-DOTA) Improves Model Generalization in Digital Pathology

no code implementations • 3 May 2023 • Sai Chowdary Gullapally, Yibo Zhang, Nitin Kumar Mittal, Deeksha Kartik, Sandhya Srinivasan, Kevin Rose, Daniel Shenker, Dinkar Juyal, Harshith Padigela, Raymond Biju, Victor Minden, Chirag Maheshwari, Marc Thibault, Zvi Goldstein, Luke Novak, Nidhi Chandra, Justin Lee, Aaditya Prakash, Chintan Shah, John Abel, Darren Fahy, Amaro Taylor-Weiner, Anand Sampat

Machine learning algorithms have the potential to improve patient outcomes in digital pathology.

AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentation

no code implementations • 21 Jul 2021 • Viraj Prabhu, Shivam Khare, Deeksha Kartik, Judy Hoffman

Most modern approaches for domain adaptive semantic segmentation rely on continued access to source data during adaptation, which may be infeasible due to computational or privacy constraints.

Segmentation Semantic Segmentation +1

SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation

2 code implementations • ICCV 2021 • Viraj Prabhu, Shivam Khare, Deeksha Kartik, Judy Hoffman

Many existing approaches for unsupervised domain adaptation (UDA) focus on adapting under only data distribution shift and offer limited success under additional cross-domain label distribution shift.

Pseudo Label Unsupervised Domain Adaptation