SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.18853 · CVPR · 2024

Rethinking Multi-domain Generalization with A General Learning Objective

Kaizhu Huang, Xi Yang, Zhaorui Tan

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

Multi-domain generalization (mDG) is universally aimed to minimize the discrepancy between training and testing distributions to enhance marginal-to-label distribution mapping. However, existing mDG literature lacks a general learning objective paradigm and often imposes constraints on static target marginal distributions. In this paper, we propose to leverage a Y-mapping to relax the constraint. We rethink the learning objective for mDG and design a new general learning objective to interpret and analyze most existing mDG wisdom. This general objective is bifurcated into two synergistic amis: learning domainindependent conditional features and maximizing a posterior. Explorations also extend to two effective regularization terms that incorporate prior information and suppress invalid causality, alleviating the issues that come with relaxed constraints. We theoretically contribute an upper bound for the domain alignment of domain-independent conditional features, disclosing that many previous mDG endeavors actually optimize partially the objective and thus lead to limited performance. As such, our study distills a general learning objective into four practical components, providing a general, robust, and flexible mechanism to handle complex domain shifts. Extensive empirical results indicate that the proposed objective with Y-mapping leads to substantially better mDG performance in various downstream tasks, including regression, segmentation, and classification. Code is available at https://github.com/ zhaorui-tan/GMDG/tree/main.

For agents

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

get_harvested_code_for_paper("2402.18853")
get_code_for_paper("2402.18853")
have("2402.18853")

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

curl https://syntology.ai/api/ran/2402.18853.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.18853.svg)](https://syntology.ai/paper/2402.18853)

Connect an agent — have() is free.