Abstract:
Existing fine-grained categorization models require extra manual annotation in addition to the image category labels. To solve this problem, we propose a novel deep transfer learning model, which transfers the learned representations from large-scale labelled fine-grained datasets to micro fine-grained datasets. Firstly, we introduce a cohesion domain to measure the degree of correlation between source domain and target domain. Secondly, select the transferrable feature that are suitable for the target domain based on the correlation. Finally, we make most of perspective-class labels for auxiliary learning, and learn all the attributes through joint learning to extract more feature representations. The experiments show that our model not only achieves high categorization accuracy but also economizes training time effectively, it also verifies the conclusion that the inter-domain feature transition can accelerate learning and optimization.
E-mail Alert
RSS
Abstract: Existing fine-grained categorization models require extra manual annotation in addition to the image category labels. To solve this problem, we propose a novel deep transfer learning model, which transfers the learned representations from large-scale labelled fine-grained datasets to micro fine-grained datasets. Firstly, we introduce a cohesion domain to measure the degree of correlation between source domain and target domain. Secondly, select the transferrable feature that are suitable for the target domain based on the correlation. Finally, we make most of perspective-class labels for auxiliary learning, and learn all the attributes through joint learning to extract more feature representations. The experiments show that our model not only achieves high categorization accuracy but also economizes training time effectively, it also verifies the conclusion that the inter-domain feature transition can accelerate learning and optimization.
