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

04/20/2023
by   Goirik Chakrabarty, et al.
0

Adapting a trained model to perform satisfactorily on continually changing testing domains/environments is an important and challenging task. In this work, we propose a novel framework, SATA, which aims to satisfy the following characteristics required for online adaptation: 1) can work seamlessly with different (preferably small) batch sizes to reduce latency; 2) should continue to work well for the source domain; 3) should have minimal tunable hyper-parameters and storage requirements. Given a pre-trained network trained on source domain data, the proposed SATA framework modifies the batch-norm affine parameters using source anchoring based self-distillation. This ensures that the model incorporates the knowledge of the newly encountered domains, without catastrophically forgetting about the previously seen ones. We also propose a source-prototype driven contrastive alignment to ensure natural grouping of the target samples, while maintaining the already learnt semantic information. Extensive evaluation on three benchmark datasets under challenging settings justify the effectiveness of SATA for real-world applications.

READ FULL TEXT
research
03/26/2021

VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation

Domain adaptation aims to leverage a label-rich domain (the source domai...
research
06/23/2021

Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentation

Unsupervised domain adaptation (UDA) aims to transfer knowledge learned ...
research
04/25/2022

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

Unsupervised Domain Adaptation (UDA) is a transfer learning task which a...
research
03/20/2023

Feature Alignment and Uniformity for Test Time Adaptation

Test time adaptation (TTA) aims to adapt deep neural networks when recei...
research
05/22/2023

Imbalance-Agnostic Source-Free Domain Adaptation via Avatar Prototype Alignment

Source-free Unsupervised Domain Adaptation (SF-UDA) aims to adapt a well...
research
11/23/2022

Robust Mean Teacher for Continual and Gradual Test-Time Adaptation

Since experiencing domain shifts during test-time is inevitable in pract...
research
04/12/2019

ACE: Adapting to Changing Environments for Semantic Segmentation

Deep neural networks exhibit exceptional accuracy when they are trained ...

Please sign up or login with your details

Forgot password? Click here to reset