# Deep Domain Adaptation by Geodesic Distance Minimization

arXiv: https://arxiv.org/abs/1707.09842 · HTML: https://mlsanity.com/paper/1707.09842/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2017.

## Built on by (most cited first, 17 of 17)

- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [PODA: Prompt-driven Zero-shot Domain Adaptation](https://mlsanity.com/paper/2212.03241/) (2022)
- [Unified Language-driven Zero-shot Domain Adaptation](https://mlsanity.com/paper/2404.07155/) (2024)
- [Unsupervised Domain Adaptation with Variational Approximation for Cardiac Segmentation](https://mlsanity.com/paper/2106.08752/) (2021)
- [SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation](https://mlsanity.com/paper/2304.03251/) (2023)
- [See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation](https://mlsanity.com/paper/2111.09450/) (2021)
- [Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation](https://mlsanity.com/paper/2409.04409/) (2024)
- [Assessing Domain Gap for Continual Domain Adaptation in Object Detection](https://mlsanity.com/paper/2302.10396/) (2023)
- [Domain Adaptation for Object Detection using SE Adaptors and Center Loss](https://mlsanity.com/paper/2205.12923/) (2022)
- [Domain Adaptation with a Single Vision-Language Embedding](https://mlsanity.com/paper/2410.21361/) (2024)
- [Prmpt2Adpt: Prompt-Based Zero-Shot Domain Adaptation for Resource-Constrained Environments](https://mlsanity.com/paper/2506.16994/) (2025)
- [PMaF: Deep Declarative Layers for Principal Matrix Features](https://mlsanity.com/paper/2306.14759/) (2023)
- [centroIDA: Cross-Domain Class Discrepancy Minimization Based on Accumulative Class-Centroids for Imbalanced Domain Adaptation](https://mlsanity.com/paper/2308.10619/) (2023)
- [Utilizing Graph Generation for Enhanced Domain Adaptive Object Detection](https://mlsanity.com/paper/2406.06535/) (2024)
- [Curvature Diversity-Driven Deformation and Domain Alignment for Point Cloud](https://mlsanity.com/paper/2410.02720/) (2024)
- [Two stages domain invariant representation learners solve the large co-variate shift in unsupervised domain adaptation with two dimensional data domains](https://mlsanity.com/paper/2412.04682/) (2024)
- [Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains](https://mlsanity.com/paper/2505.21010/) (2025)

## Abstract (arXiv)

In this paper, we propose a new approach called Deep LogCORAL for unsupervised visual domain adaptation. Our work builds on the recently proposed Deep CORAL method, which proposed to train a convolutional neural network and simultaneously minimize the Euclidean distance of convariance matrices between the source and target domains. We propose to use the Riemannian distance, approximated by Log-Euclidean distance, to replace the naive Euclidean distance in Deep CORAL. We also consider first-order information, and minimize the distance of mean vectors between two domains. We build an end-to-end model, in which we minimize both the classification loss, and the domain difference based on the first and second order information between two domains. Our experiments on the benchmark Office dataset demonstrate the improvements of our newly proposed Deep LogCORAL approach over the Deep CORAL method, as well as further improvement when optimizing both orders of information.