MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation Article Swipe

MAKE IMPACT

Lukas Hoyer , Dengxin Dai , Haoran Wang , Luc Van Gool · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2212.01322

In unsupervised domain adaptation (UDA), a model trained on source data (e.g. synthetic) is adapted to target data (e.g. real-world) without access to target annotation. Most previous UDA methods struggle with classes that have a similar visual appearance on the target domain as no ground truth is available to learn the slight appearance differences. To address this problem, we propose a Masked Image Consistency (MIC) module to enhance UDA by learning spatial context relations of the target domain as additional clues for robust visual recognition. MIC enforces the consistency between predictions of masked target images, where random patches are withheld, and pseudo-labels that are generated based on the complete image by an exponential moving average teacher. To minimize the consistency loss, the network has to learn to infer the predictions of the masked regions from their context. Due to its simple and universal concept, MIC can be integrated into various UDA methods across different visual recognition tasks such as image classification, semantic segmentation, and object detection. MIC significantly improves the state-of-the-art performance across the different recognition tasks for synthetic-to-real, day-to-nighttime, and clear-to-adverse-weather UDA. For instance, MIC achieves an unprecedented UDA performance of 75.9 mIoU and 92.8% on GTA-to-Cityscapes and VisDA-2017, respectively, which corresponds to an improvement of +2.1 and +3.0 percent points over the previous state of the art. The implementation is available at https://github.com/lhoyer/MIC.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2212.01322

PDF

https://arxiv.org/pdf/2212.01322

OA Status

green

Cited By

9

Related Works

10

OpenAlex ID

https://openalex.org/W4310746793

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4310746793

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2212.01322

Digital Object Identifier

Title

MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2022

Year of publication

Publication date

2022-12-02

Full publication date if available

Authors

Lukas Hoyer, Dengxin Dai, Haoran Wang, Luc Van Gool

List of authors in order

Landing page

https://arxiv.org/abs/2212.01322

Publisher landing page

PDF URL

https://arxiv.org/pdf/2212.01322

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2212.01322

Direct OA link when available

Concepts

Computer science, Consistency (knowledge bases), Context (archaeology), Artificial intelligence, Segmentation, Ground truth, Adaptation (eye), Domain (mathematical analysis), Pattern recognition (psychology), Annotation, Image (mathematics), Object (grammar), Computer vision, Mathematics, Geography, Archaeology, Physics, Optics, Mathematical analysis

Top concepts (fields/topics) attached by OpenAlex

Cited by

9

Total citation count in OpenAlex

Citations by year (recent)

2025: 2, 2024: 5, 2023: 2

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload