# Self-training solutions for the ICCV 2023 GeoNet Challenge

arXiv: https://arxiv.org/abs/2311.16843 · HTML: https://mlsanity.com/paper/2311.16843/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 4 references that are in the map.
- First posted on arXiv 28 Nov 2023.

## Builds on (most cited first, 3 of 3)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [GeoNet: Benchmarking Unsupervised Adaptation across Geographies](https://mlsanity.com/paper/2303.15443/) (2023)

## Abstract (arXiv)

GeoNet is a recently proposed domain adaptation benchmark consisting of three challenges (i.e., GeoUniDA, GeoImNet, and GeoPlaces). Each challenge contains images collected from the USA and Asia where there are huge geographical gaps. Our solution adopts a two-stage source-free domain adaptation framework with a Swin Transformer backbone to achieve knowledge transfer from the USA (source) domain to Asia (target) domain. In the first stage, we train a source model using labeled source data with a re-sampling strategy and two types of cross-entropy loss. In the second stage, we generate pseudo labels for unlabeled target data to fine-tune the model. Our method achieves an H-score of 74.56% and ultimately ranks 1st in the GeoUniDA challenge. In GeoImNet and GeoPlaces challenges, our solution also reaches a top-3 accuracy of 64.46% and 51.23%, respectively.