SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.11389 · 2022

TTTFlow: Unsupervised Test-Time Training with Normalizing Flow

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2210.11389")
get_code_for_paper("2210.11389")
have("2210.11389")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2210.11389.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2210.11389.svg)](https://syntology.ai/paper/2210.11389)

Connect an agent — have() is free.