VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data

07/23/2021
by   Dina Bashkirova, et al.
0

Progress in machine learning is typically measured by training and testing a model on the same distribution of data, i.e., the same domain. This over-estimates future accuracy on out-of-distribution data. The Visual Domain Adaptation (VisDA) 2021 competition tests models' ability to adapt to novel test distributions and handle distributional shift. We set up unsupervised domain adaptation challenges for image classifiers and will evaluate adaptation to novel viewpoints, backgrounds, modalities and degradation in quality. Our challenge draws on large-scale publicly available datasets but constructs the evaluation across domains, rather that the traditional in-domain bench-marking. Furthermore, we focus on the difficult "universal" setting where, in addition to input distribution drift, methods may encounter missing and/or novel classes in the target dataset. Performance will be measured using a rigorous protocol, comparing to state-of-the-art domain adaptation methods with the help of established metrics. We believe that the competition will encourage further improvement in machine learning methods' ability to handle realistic data in many deployment scenarios.

READ FULL TEXT
research
10/18/2017

VisDA: The Visual Domain Adaptation Challenge

We present the 2017 Visual Domain Adaptation (VisDA) dataset and challen...
research
12/18/2021

Pre-Training Transformers for Domain Adaptation

The Visual Domain Adaptation Challenge 2021 called for unsupervised doma...
research
10/27/2021

2nd Place Solution for VisDA 2021 Challenge – Universally Domain Adaptive Image Recognition

The Visual Domain Adaptation (VisDA) 2021 Challenge calls for unsupervis...
research
06/19/2019

Domain Adaptation for Enterprise Email Search

In the enterprise email search setting, the same search engine often pow...
research
07/11/2023

MoP-CLIP: A Mixture of Prompt-Tuned CLIP Models for Domain Incremental Learning

Despite the recent progress in incremental learning, addressing catastro...
research
03/26/2023

VisDA 2022 Challenge: Domain Adaptation for Industrial Waste Sorting

Label-efficient and reliable semantic segmentation is essential for many...
research
08/20/2013

Towards Adapting ImageNet to Reality: Scalable Domain Adaptation with Implicit Low-rank Transformations

Images seen during test time are often not from the same distribution as...

Please sign up or login with your details

Forgot password? Click here to reset