# Impact of ImageNet Model Selection on Domain Adaptation

arXiv: https://arxiv.org/abs/2002.02559 · HTML: https://mlsanity.com/paper/2002.02559/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2020.

## Built on by (most cited first, 15 of 15)

- [Do better ImageNet classifiers assess perceptual similarity better?](https://mlsanity.com/paper/2203.04946/) (2022)
- [A Survey of Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2112.06745/) (2021)
- [Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey](https://mlsanity.com/paper/2412.13840/) (2024)
- [Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence](https://mlsanity.com/paper/2412.13779/) (2024)
- [Resource-Constrained Federated Continual Learning: What Does Matter?](https://mlsanity.com/paper/2501.08737/) (2025)
- [Efficient Pre-trained Features and Recurrent Pseudo-Labeling in Unsupervised Domain Adaptation](https://mlsanity.com/paper/2104.13486/) (2021)
- [Adversarial Regression Learning for Bone Age Estimation](https://mlsanity.com/paper/2103.06149/) (2021)
- [Deep Least Squares Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2111.02207/) (2021)
- [Correlated Adversarial Joint Discrepancy Adaptation Network](https://mlsanity.com/paper/2105.08808/) (2021)
- [Key Design Choices for Double-Transfer in Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2302.05379/) (2023)
- [Key Design Choices in Source-Free Unsupervised Domain Adaptation: An In-depth Empirical Analysis](https://mlsanity.com/paper/2402.16090/) (2024)
- [Self-supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets?](https://mlsanity.com/paper/2501.15431/) (2025)
- [House Price Prediction Based On Deep Learning](https://mlsanity.com/paper/2204.09050/) (2022)
- [Deep Feature Registration for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2310.16100/) (2023)
- [Federated Active Learning for Target Domain Generalisation](https://mlsanity.com/paper/2312.02247/) (2023)

## Abstract (arXiv)

Deep neural networks are widely used in image classification problems. However, little work addresses how features from different deep neural networks affect the domain adaptation problem. Existing methods often extract deep features from one ImageNet model, without exploring other neural networks. In this paper, we investigate how different ImageNet models affect transfer accuracy on domain adaptation problems. We extract features from sixteen distinct pre-trained ImageNet models and examine the performance of twelve benchmarking methods when using the features. Extensive experimental results show that a higher accuracy ImageNet model produces better features, and leads to higher accuracy on domain adaptation problems (with a correlation coefficient of up to 0.95). We also examine the architecture of each neural network to find the best layer for feature extraction. Together, performance from our features exceeds that of the state-of-the-art in three benchmark datasets.