Master of All : Simultaneous Generalization of Urban-Scene Segmentation | ECCV 2022

Paper Abstract:
Computer vision systems for autonomous navigation must generalize well in adverse weather and illumination conditions expected in the real world. However, semantic segmentation of images captured in such conditions remains a challenging task for current state-of-the-art (SOTA) methods trained on broad daylight images, due to the associated distribution shift. To remedy this, we propose a novel, fully test time adaptation technique, named Master of ALL (MALL), for simultaneous generalization to multiple target domains. MALL learns to generalize on unseen adverse weather images from multiple target domains directly at the inference time. More specifically, given a pre-trained model and its parameters, MALL enforces edge consistency prior at the inference stage and updates the model based on (a) a single test sample at a time (MALL-sample), or (b) continuously for the whole test domain (MALL-domain).
Speaker Bio:
Nikhil Reddy is a Ph.D. student at the University of Queensland - IIT Delhi research academy. His research focuses on incorporating geometric priors into urban scene understanding. His thesis supervisors are Prof. Chetan Arora (IIT Delhi) and Prof. Mahsa Baktashmotlagh (University of Queensland). His master’s thesis is based on improving explainability In machine learning classifiers.
Paper Link: www.cse.iitd.ac.in/~chetan/pa...
Project page: mall-iitd.github.io/