# Residual Parameter Transfer for Deep Domain Adaptation

arXiv: https://arxiv.org/abs/1711.07714 · HTML: https://mlsanity.com/paper/1711.07714/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2017.

## Built on by (most cited first, 8 of 8)

- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [Learn to Ignore: Domain Adaptation for Multi-Site MRI Analysis](https://mlsanity.com/paper/2110.06803/) (2021)
- [Efficient Low-Resolution Face Recognition via Bridge Distillation](https://mlsanity.com/paper/2409.11786/) (2024)
- [Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation](https://mlsanity.com/paper/2108.02980/) (2021)
- [MetaPix: Domain Transfer for Semantic Segmentation by Meta Pixel Weighting](https://mlsanity.com/paper/2110.01777/) (2021)
- [A Cross-City Federated Transfer Learning Framework: A Case Study on Urban Region Profiling](https://mlsanity.com/paper/2206.00007/) (2022)
- [Self-Paced Collaborative and Adversarial Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2506.19267/) (2025)
- [Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints](https://mlsanity.com/paper/2609.01014/) (2026)

## Abstract (arXiv)

The goal of Deep Domain Adaptation is to make it possible to use Deep Nets trained in one domain where there is enough annotated training data in another where there is little or none. Most current approaches have focused on learning feature representations that are invariant to the changes that occur when going from one domain to the other, which means using the same network parameters in both domains. While some recent algorithms explicitly model the changes by adapting the network parameters, they either severely restrict the possible domain changes, or significantly increase the number of model parameters. By contrast, we introduce a network architecture that includes auxiliary residual networks, which we train to predict the parameters in the domain with little annotated data from those in the other one. This architecture enables us to flexibly preserve the similarities between domains where they exist and model the differences when necessary. We demonstrate that our approach yields higher accuracy than state-of-the-art methods without undue complexity.