TTTFlow: Unsupervised Test-Time Training with Normalizing Flow
A major problem of deep neural networks for image classification is their vulnerability to domain changes at test-time. Recent methods have proposed to address this problem with test-time training (TTT), where a two-branch model is trained to learn a main classification task and also a self-supervised task used to perform test-time adaptation. However, these techniques require defining a proxy task specific to the target application. To tackle this limitation, we propose TTTFlow: a Y-shaped architecture using an unsupervised head based on Normalizing Flows to learn the normal distribution of latent features and detect domain shifts in test examples. At inference, keeping the unsupervised head fixed, we adapt the model to domain-shifted examples by maximizing the log likelihood of the Normalizing Flow. Our results show that our method can significantly improve the accuracy with respect to previous works.
Code (1)
Tasks
image-classificationImage ClassificationSource-Free Domain AdaptationTest-time AdaptationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Harmonizing Flows: Unsupervised MR harmonization based on normalizing flows
In this paper, we propose an unsupervised framework based on normalizing flows that harmonizes MR images to mimic the distribution of the source domain. The proposed framework consists of three steps. First, a shallow ha…
MRI segmentationCT-3DFlow : Leveraging 3D Normalizing Flows for Unsupervised Detection of Pathological Pulmonary CT scans
Unsupervised pathology detection can be implemented by training a model on healthy data only and measuring the deviation from the training set upon inference, for example with CNN-based feature extraction and one-class c…
Out-of-Distribution DetectionAltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for Anomaly Detection
Unsupervised anomaly detection is coming into the spotlight these days in various practical domains due to the limited amount of anomaly data. One of the major approaches for it is a normalizing flow which pursues the in…
Anomaly DetectionAnomaly SegmentationUnsupervised Anomaly DetectionFlow-Adapter Architecture for Unsupervised Machine Translation
In this work, we propose a flow-adapter architecture for unsupervised NMT. It leverages normalizing flows to explicitly model the distributions of sentence-level latent representations, which are subsequently used in con…
Machine TranslationNMTSentenceTranslation+1The Practicality of Normalizing Flow Test-Time Training in Bayesian Inference for Agent-Based Models
Agent-Based Models (ABMs) are gaining great popularity in economics and social science because of their strong flexibility to describe the realistic and heterogeneous decisions and interaction rules between individual ag…
Bayesian Inference