DeepAI AI Chat
Log In Sign Up

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

by   Goirik Chakrabarty, et al.

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.


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

Domain adaptation aims to leverage a label-rich domain (the source domai...

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

Unsupervised domain adaptation (UDA) aims to transfer knowledge learned ...

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

Unsupervised Domain Adaptation (UDA) is a transfer learning task which a...

Feature Alignment and Uniformity for Test Time Adaptation

Test time adaptation (TTA) aims to adapt deep neural networks when recei...

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

Source-free Unsupervised Domain Adaptation (SF-UDA) aims to adapt a well...

Robust Mean Teacher for Continual and Gradual Test-Time Adaptation

Since experiencing domain shifts during test-time is inevitable in pract...

ACE: Adapting to Changing Environments for Semantic Segmentation

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