Impact of ImageNet Model Selection on Domain Adaptation
This work addresses the problem of model selection for domain adaptation in image classification, but it is incremental as it builds on existing pre-trained models and benchmarking methods.
The paper investigates how features from different pre-trained ImageNet models affect domain adaptation accuracy, finding that higher-accuracy models yield better features with a correlation coefficient up to 0.95, and using these features outperforms state-of-the-art methods on three benchmark datasets.
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.