DeepAI AI Chat
Log In Sign Up

Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation

by   Antoine Saporta, et al.

Unsupervised Domain Adaptation (UDA) is a transfer learning task which aims at training on an unlabeled target domain by leveraging a labeled source domain. Beyond the traditional scope of UDA with a single source domain and a single target domain, real-world perception systems face a variety of scenarios to handle, from varying lighting conditions to many cities around the world. In this context, UDAs with several domains increase the challenges with the addition of distribution shifts within the different target domains. This work focuses on a novel framework for learning UDA, continuous UDA, in which models operate on multiple target domains discovered sequentially, without access to previous target domains. We propose MuHDi, for Multi-Head Distillation, a method that solves the catastrophic forgetting problem, inherent in continual learning tasks. MuHDi performs distillation at multiple levels from the previous model as well as an auxiliary target-specialist segmentation head. We report both extensive ablation and experiments on challenging multi-target UDA semantic segmentation benchmarks to validate the proposed learning scheme and architecture.


page 1

page 2

page 3

page 4


Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation

Multi-source unsupervised domain adaptation (MSDA) aims at adapting mode...

Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation

In this work, we address the task of unsupervised domain adaptation (UDA...

Multi-scale Feature Alignment for Continual Learning of Unlabeled Domains

Methods for unsupervised domain adaptation (UDA) help to improve the per...

Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation

Environment perception in autonomous driving vehicles often heavily reli...

Gradient Regularized Contrastive Learning for Continual Domain Adaptation

Human beings can quickly adapt to environmental changes by leveraging le...

SATA: Source Anchoring and Target Alignment Network for Continual Test Time Adaptation

Adapting a trained model to perform satisfactorily on continually changi...

Generative appearance replay for continual unsupervised domain adaptation

Deep learning models can achieve high accuracy when trained on large amo...