We propose FineGAN, a novel unsupervised GAN framework, which disentangles the background, object shape, and object appearance to hierarchically generate images of fine-grained object categories.
We propose a measure to estimate domain similarity via Earth Mover's Distance and demonstrate that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure.
#2 best model for Fine-Grained Image Classification on CUB-200-2011
Recognizing objects from subcategories with very subtle differences remains a challenging task due to the large intra-class and small inter-class variation.
#4 best model for Fine-Grained Image Classification on Stanford Cars
Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often difficult to acquire an enough number of training samples.
While the existing datasets for FGVC are mainly focused on animal breeds or man-made objects with limited labelled data, VegFru is a larger dataset consisting of vegetables and fruits which are closely associated with the daily life of everyone.
Food classification is a challenging problem due to the large number of categories, high visual similarity between different foods, as well as the lack of datasets for training state-of-the-art deep models.