MixMatch Domain Adaptaion: Prize-winning solution for both tracks of VisDA 2019 challenge
Not on the map. Why?
Abstract (arXiv)
We present a domain adaptation (DA) system that can be used in multi-source and semi-supervised settings. Using the proposed method we achieved 2nd place on multi-source track and 3rd place on semi-supervised track of the VisDA 2019 challenge (http://ai.bu.edu/visda-2019/). The source code of the method is available at https://github.com/filaPro/visda2019.
Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Oct 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 1; 2023: 1.
5 papers.
- 2022ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptationcited by 34
- 2021Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentationcited by 33
- 2021Semi-supervised Domain Adaptation for Semantic Segmentationcited by 4
- 2021Domain Adaptation and Active Learning for Fine-Grained Recognition in the Field of Biodiversitycited by 0
- 2023GeT: Generative Target Structure Debiasing for Domain Adaptationcited by 0
- 2023GeT: Generative Target Structure Debiasing for Domain Adaptation20 Aug 2023
- 2022ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation29 May 2022
- 2021Domain Adaptation and Active Learning for Fine-Grained Recognition in the Field of Biodiversity22 Oct 2021
- 2021Semi-supervised Domain Adaptation for Semantic Segmentation20 Oct 2021
- 2021Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation8 Mar 2021