VisDA 2022 Challenge: Domain Adaptation for Industrial Waste Sorting

Dina Bashkirova*, Samarth Mishra*, Diala Lteif*, Piotr Teterwak*, Donghyun Kim*, Fadi Alladkani, James Akl, Berk Calli, Sarah Adel Bargal, Kate Saenko, Daehan Kim, Minseok Seo, Young Jin Jeon, Dong Geol Choi, Shahaf Ettedgui, Raja Giryes, Shady Abu-Hussein, Binhui Xie, Shuang Li

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

Abstract

Label-efficient and reliable semantic segmentation is essential for many real-life applications, especially for industrial settings with high visual diversity, such as waste sorting. In industrial waste sorting, one of the biggest challenges is the extreme diversity of the input stream depending on factors like the location of the sorting facility, the equipment available in the facility, and the time of year, all of which significantly impact the composition and visual appearance of the waste stream. These changes in the data are called “visual domains”, and label-efficient adaptation of models to such domains is needed for successful semantic segmentation of industrial waste. To test the abilities of computer vision models on this task, we present the VisDA 2022 Challenge on Domain Adaptation for Industrial Waste Sorting. Our challenge incorporates a fully-annotated waste sorting dataset, ZeroWaste, collected from two real material recovery facilities in different locations and seasons, as well as a novel procedurally generated synthetic waste sorting dataset, SynthWaste. In this competition, we aim to answer two questions: 1) can we leverage domain adaptation techniques to minimize the domain gap? and 2) can synthetic data augmentation improve performance on this task and help adapt to changing data distributions? The results of the competition show that industrial waste detection poses a real domain adaptation problem, that domain generalization techniques such as augmentations, ensembling, etc., improve the overall performance on the unlabeled target domain examples, and that leveraging synthetic data effectively remains an open problem. See https://ai.bu.edu/visda-2022/

Original languageEnglish
Pages (from-to)104-118
Number of pages15
JournalProceedings of Machine Learning Research
Volume220
StatePublished - 2023
Event36th Annual Conference on Neural Information Processing Systems, NeurIPS 2022 - Virtual, Online, United States
Duration: 28 Nov 20229 Dec 2022

Funding

FundersFunder number
National Science Foundation1928477

    Keywords

    • AI for environment
    • domain adaptation
    • semantic segmentation

    Fingerprint

    Dive into the research topics of 'VisDA 2022 Challenge: Domain Adaptation for Industrial Waste Sorting'. Together they form a unique fingerprint.

    Cite this