Tent: Fully Test-time Adaptation by Entropy Minimization

2020/06/18 by Dequan Wang, Evan Shelhamer, Wang, Dequan +7 · 8 citations
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multimodal Machine Learning Applications

paper · pdf · doi:10.48550/arxiv.2006.10726

openalex publication_date 2020/06/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

A model must adapt itself to generalize to new and different data during testing. In this setting of fully test-time adaptation the model has only the test data and its own parameters. We propose to adapt by test entropy minimization (tent): we optimize the model for confidence as measured by the entropy of its predictions. Our method estimates normalization statistics and optimizes channel-wise affine transformations to update online on each batch. Tent reduces generalization error for image classification on corrupted ImageNet and CIFAR-10/100 and reaches a new state-of-the-art error on ImageNet-C. Tent handles source-free domain adaptation on digit recognition from SVHN to MNIST/MNIST-M/USPS, on semantic segmentation from GTA to Cityscapes, and on the VisDA-C benchmark. These results are achieved in one epoch of test-time optimization without altering training.

Citations

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Gradient-based learning applied to document recognition
• ImageNet Large Scale Visual Recognition Challenge
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual\n Recognition
• ImageNet classification with deep convolutional neural networks
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• Adversarial Discriminative Domain Adaptation
• Deep High-Resolution Representation Learning for Visual Recognition
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Boundary-Aware Test-Time Adaptation for Zero-Shot Medical Image Segmentation
• Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning
• Dream to Recall: Imagination-Guided Experience Retrieval for Memory-Persistent Vision-and-Language Navigation
• MEMO: Test Time Robustness via Adaptation and Augmentation
• Generalizable Model-agnostic Semantic Segmentation via Target-specific Normalization
• WILDS: A Benchmark of in-the-Wild Distribution Shifts
• RoMA: Robust Model Adaptation for Offline Model-based Optimization
• Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
• Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models

Related

• Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization
• REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation
• Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
• Ranked Entropy Minimization for Continual Test-Time Adaptation
• COME: Test-time adaption by Conservatively Minimizing Entropy