GMFAD: Towards generalized visual recognition via multilayer feature alignment and disentanglement

• المؤلفون الرئيسيون: Li, Haoliang, Wang, Shiqi, Wan, Renjie, Kot, Alex Chichung
• مؤلفون آخرون: School of Electrical and Electronic Engineering
• التنسيق: مقال
• اللغة: English
• منشور في: 2022
• الموضوعات: Engineering::Electrical and electronic engineering; Engineering::Computer science and engineering; Generalization Capability; Covariance Matrix
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/161899

The deep learning based approaches which have been repeatedly proven to bring benefits to visual recognition tasks usually make a strong assumption that the training and test data are drawn from similar feature spaces and distributions. However, such an assumption may not always hold in various prac...