EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization

03/03/2023
by   Junha Song, et al.
0

This paper presents a simple yet effective approach that improves continual test-time adaptation (TTA) in a memory-efficient manner. TTA may primarily be conducted on edge devices with limited memory, so reducing memory is crucial but has been overlooked in previous TTA studies. In addition, long-term adaptation often leads to catastrophic forgetting and error accumulation, which hinders applying TTA in real-world deployments. Our approach consists of two components to address these issues. First, we present lightweight meta networks that can adapt the frozen original networks to the target domain. This novel architecture minimizes memory consumption by decreasing the size of intermediate activations required for backpropagation. Second, our novel self-distilled regularization controls the output of the meta networks not to deviate significantly from the output of the frozen original networks, thereby preserving well-trained knowledge from the source domain. Without additional memory, this regularization prevents error accumulation and catastrophic forgetting, resulting in stable performance even in long-term test-time adaptation. We demonstrate that our simple yet effective strategy outperforms other state-of-the-art methods on various benchmarks for image classification and semantic segmentation tasks. Notably, our proposed method with ResNet-50 and WideResNet-40 takes 86 state-of-the-art method, CoTTA.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/18/2023

Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation

Continual Test-Time Adaptation (CTTA) generalizes conventional Test-Time...
research
12/08/2022

Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation

Continual Test-Time Adaptation (CTTA) aims to adapt the source model to ...
research
08/14/2023

Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization

Test-time adaptation (TTA) methods, which generally rely on the model's ...
research
04/13/2023

CoSDA: Continual Source-Free Domain Adaptation

Without access to the source data, source-free domain adaptation (SFDA) ...
research
12/19/2022

A Probabilistic Framework for Lifelong Test-Time Adaptation

Test-time adaptation is the problem of adapting a source pre-trained mod...
research
05/26/2023

Mitigating Catastrophic Forgetting in Long Short-Term Memory Networks

Continual learning on sequential data is critical for many machine learn...
research
10/06/2020

Efficient Meta Lifelong-Learning with Limited Memory

Current natural language processing models work well on a single task, y...

Please sign up or login with your details

Forgot password? Click here to reset