Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine grained Visual Categorization

Fine-Grained Visual Categorization (FGVC) is a challenging topic in computer vision . We show competitive improvement on accuracy by using attention-aware data augmentation techniques with features derived from deep learning model InceptionV3, pre-trained on large scale datasets . Our method outperforms competitor methods on multiple FGVC datasets and showed competitive results on other datasets. Our method achieves state-of-the-art results in multiple fine-grained classification datasets including challenging CUB200-2011 bird, Flowers-102, and FGVC-Aircrafts datasets . We perform domain adaptive knowledge transfer via fine-tuning on our base network model. We present a comprehensive analysis of our experiments. We also show competitive results in several FGVC dataset. We hope to use our method to solve the problem in the next step in the future to improve our understanding of our findings.

Links: PDF - Abstract

Code :


Keywords : datasets - fgvc - fine - method - competitive -

Leave a Reply

Your email address will not be published. Required fields are marked *