Deep Collaborative Weight-based Classification.
Year: 2018
Type: preprint
Abstract: One of the biggest problems in deep learning is its difficulty to retain consistent robustness when transferring the model trained on one dataset to another dataset. To conquer the problem, deep transfer learning was implemented to execute various vision tasks by using a pre-trained deep model in a diverse dataset. However, the robustness was often far from state-of-the-art. We propose a collaborative weight-based classification method for deep transfer learning (DeepCWC). The method performs the L2-norm based collaborative representation on the original images, as well as the deep features extracted by pre-trained deep models. Two distance vectors will be obtained based on the two representation coefficients, and then fused together via the collaborative weight. The two feature sets show a complementary character, and the original images provide information compensating the missed part in the transferred deep model. A series of experiments conducted on both small and large vision datasets demonstrated the robustness of the proposed DeepCWC in both face recognition and object recognition tasks.
Source: arXiv (Cornell University)
Authors: Shaoning Zeng, Bob Zhang, Jianping Gou
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2788832490