Bag of Tricks for Out-of-Distribution Generalization

TL;DR

This paper introduces a simple, effective, and memory-efficient framework using a combination of tricks for out-of-distribution generalization, achieving top performance on the NICO++ dataset without complex modules or large pre-trained models.

Contribution

It proposes a coupling of multiple strategies into a unified framework for OOD generalization, simplifying the approach while maintaining high performance.

Findings

Achieved 88.16% Top-1 accuracy on public test set

Achieved 75.65% Top-1 accuracy on private test set

Ranked 1st in the NICOchallenge-2022 domain generalization task

Abstract

Recently, out-of-distribution (OOD) generalization has attracted attention to the robustness and generalization ability of deep learning based models, and accordingly, many strategies have been made to address different aspects related to this issue. However, most existing algorithms for OOD generalization are complicated and specifically designed for certain dataset. To alleviate this problem, nicochallenge-2022 provides NICO++, a large-scale dataset with diverse context information. In this paper, based on systematic analysis of different schemes on NICO++ dataset, we propose a simple but effective learning framework via coupling bag of tricks, including multi-objective framework design, data augmentations, training and inference strategies. Our algorithm is memory-efficient and easily-equipped, without complicated modules and does not require for large pre-trained models. It achieves an excellent performance with Top-1 accuracy of 88.16% on public test set and 75.65% on private test set, and ranks 1st in domain generalization task of nicochallenge-2022.