CAFA: Class-Aware Feature Alignment for Test-Time Adaptation

06/01/2022
by   Sanghun Jung, et al.
0

Despite recent advancements in deep learning, deep networks still suffer from performance degradation when they face new and different data from their training distributions. Addressing such a problem, test-time adaptation (TTA) aims to adapt a model to unlabeled test data on test time while making predictions simultaneously. TTA applies to pretrained networks without modifying their training procedures, which enables to utilize the already well-formed source distribution for adaptation. One possible approach is to align the representation space of test samples to the source distribution (i.e., feature alignment). However, performing feature alignments in TTA is especially challenging in that the access to labeled source data is restricted during adaptation. That is, a model does not have a chance to learn test data in a class-discriminative manner, which was feasible in other adaptation tasks (e.g., unsupervised domain adaptation) via supervised loss on the source data. Based on such an observation, this paper proposes a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which 1) encourages a model to learn target representations in a class-discriminative manner and 2) effectively mitigates the distribution shifts in test time, simultaneously. Our method does not require any hyper-parameters or additional losses, which are required in the previous approaches. We conduct extensive experiments and show our proposed method consistently outperforms existing baselines.

READ FULL TEXT
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
06/28/2022

Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment

Vision Transformer (ViT) is becoming more popular in image processing. S...
research
04/28/2022

Covariance-aware Feature Alignment with Pre-computed Source Statistics for Test-time Adaptation

The accuracy of deep neural networks is degraded when the distribution o...
research
03/29/2023

TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation

Test-time adaptation methods have been gaining attention recently as a p...
research
02/23/2023

Unsupervised Domain Adaptation via Distilled Discriminative Clustering

Unsupervised domain adaptation addresses the problem of classifying data...
research
03/24/2023

Robust Test-Time Adaptation in Dynamic Scenarios

Test-time adaptation (TTA) intends to adapt the pretrained model to test...
research
11/21/2022

MATE: Masked Autoencoders are Online 3D Test-Time Learners

We propose MATE, the first Test-Time-Training (TTT) method designed for ...

Please sign up or login with your details

Forgot password? Click here to reset