SimpleDG: Simple Domain Generalization Baseline without Bells and Whistles

10/26/2022
by   Zhi Lv, et al.
0

We present a simple domain generalization baseline, which wins second place in both the common context generalization track and the hybrid context generalization track respectively in NICO CHALLENGE 2022. We verify the founding in recent literature, domainbed, that ERM is a strong baseline compared to recent state-of-the-art domain generalization methods and propose SimpleDG which includes several simple yet effective designs that further boost generalization performance. Code is available at https://github.com/megvii-research/SimpleDG

READ FULL TEXT
research
04/26/2021

Yes, BM25 is a Strong Baseline for Legal Case Retrieval

We describe our single submission to task 1 of COLIEE 2021. Our vanilla ...
research
10/09/2019

MixMatch Domain Adaptaion: Prize-winning solution for both tracks of VisDA 2019 challenge

We present a domain adaptation (DA) system that can be used in multi-sou...
research
06/22/2023

Pruning for Better Domain Generalizability

In this paper, we investigate whether we could use pruning as a reliable...
research
08/22/2023

Domain Generalization via Rationale Invariance

This paper offers a new perspective to ease the challenge of domain gene...
research
04/01/2023

From Zero to Hero: Convincing with Extremely Complicated Math

Becoming a (super) hero is almost every kid's dream. During their shelte...
research
03/31/2023

Simple Domain Generalization Methods are Strong Baselines for Open Domain Generalization

In real-world applications, a machine learning model is required to hand...
research
06/27/2023

ShuttleSet22: Benchmarking Stroke Forecasting with Stroke-Level Badminton Dataset

In recent years, badminton analytics has drawn attention due to the adva...

Please sign up or login with your details

Forgot password? Click here to reset