paper-with-me

Papers

TTTFlow: Unsupervised Test-Time Training with Normalizing Flow

2022-10-20 · David Osowiechi, Gustavo A. Vargas Hakim, Mehrdad Noori, Milad Cheraghalikhani, Ismail Ben Ayed, Christian Desrosiers

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.

📄 PDF Abstract BibTeX arXiv:2210.11389

Code (1)

gustavovargashakim/tttflow 공식 구현 pytorch

Tasks

image-classificationImage ClassificationSource-Free Domain AdaptationTest-time Adaptation

Methods 이 논문이 사용한 방법론

Test 설명 없음
Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…

Similar Papers 제목 키워드 기반

Harmonizing Flows: Unsupervised MR harmonization based on normalizing flows

2023-01-27 · Farzad Beizaee, Christian Desrosiers, Gregory A. Lodygensky, Jose Dolz

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 segmentation

CT-3DFlow : Leveraging 3D Normalizing Flows for Unsupervised Detection of Pathological Pulmonary CT scans

2024-03-27 · Aissam Djahnine, Alexandre Popoff, Emilien Jupin-Delevaux, Vincent Cottin 외

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 Detection

AltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for Anomaly Detection

2022-10-26 · Yeongmin Kim, Huiwon Jang, DongKeon Lee, Ho-Jin Choi

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 Detection

Flow-Adapter Architecture for Unsupervised Machine Translation

2022-04-26 · ACL 2022 5 · Yihong Liu, Haris Jabbar, Hinrich Schütze

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+1

The Practicality of Normalizing Flow Test-Time Training in Bayesian Inference for Agent-Based Models

2026-01-12 · Junyao Zhang, Jinglai Li, Junqi Tang arxiv

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