SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.02811 · ICCV · 2021

CrossNorm and SelfNorm for Generalization under Distribution Shifts

Dimitris Metaxas, Yi Zhu, Mu Li, Zhi Zhang, Zhiqiang Tang, Yunhe Gao

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

Traditional normalization techniques (e.g., Batch Normalization and Instance Normalization) generally and simplistically assume that training and test data follow the same distribution. As distribution shifts are inevitable in real-world applications, well-trained models with previous normalization methods can perform badly in new environments. Can we develop new normalization methods to improve generalization robustness under distribution shifts? In this paper, we answer the question by proposing Cross-Norm and SelfNorm. CrossNorm exchanges channel-wise mean and variance between feature maps to enlarge training distribution, while SelfNorm uses attention to recalibrate the statistics to bridge gaps between training and test distributions. CrossNorm and SelfNorm can complement each other, though exploring different directions in statistics usage. Extensive experiments on different fields (vision and language), tasks (classification and segmentation), settings (supervised and semi-supervised), and distribution shift types (synthetic and natural) show the effectiveness. Code is available at https://github.com/ amazon-research/crossnorm-selfnorm

For agents

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

get_harvested_code_for_paper("2102.02811")
get_code_for_paper("2102.02811")
have("2102.02811")

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

curl https://syntology.ai/api/ran/2102.02811.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.02811.svg)](https://syntology.ai/paper/2102.02811)

Connect an agent — have() is free.