Modified Distribution Alignment for Domain Adaptation with Pre-trained Inception ResNet
This addresses the problem of adapting image recognition models across domains, but it is incremental as it builds on existing pre-trained networks and alignment methods.
The paper tackled domain adaptation for image recognition by using a pre-trained Inception ResNet to extract features and a modified distribution alignment method, achieving improvements of 4.8%, 5.5%, and 10% in accuracy on benchmark datasets.
Deep neural networks have been widely used in computer vision. There are several well trained deep neural networks for the ImageNet classification challenge, which has played a significant role in image recognition. However, little work has explored pre-trained neural networks for image recognition in domain adaption. In this paper, we are the first to extract better-represented features from a pre-trained Inception ResNet model for domain adaptation. We then present a modified distribution alignment method for classification using the extracted features. We test our model using three benchmark datasets (Office+Caltech-10, Office-31, and Office-Home). Extensive experiments demonstrate significant improvements (4.8%, 5.5%, and 10%) in classification accuracy over the state-of-the-art.