Deep Mutual Learning

• Main Authors: Zhang, Ying, Xiang, Tao, Hospedales, Timothy M., Lu, Huchuan
• Format: Report
• Language: unknown
• Published: arXiv 2017
• Subjects: Computer Vision and Pattern Recognition cs.CV; FOS Computer and information sciences; DML
• Online Access: https://dx.doi.org/10.48550/arxiv.1706.00384; https://arxiv.org/abs/1706.00384

Model distillation is an effective and widely used technique to transfer knowledge from a teacher to a student network. The typical application is to transfer from a powerful large network or ensemble to a small network, that is better suited to low-memory or fast execution requirements. In this paper, we present a deep mutual learning (DML) strategy where, rather than one way transfer between a static pre-defined teacher and a student, an ensemble of students learn collaboratively and teach each other throughout the training process. Our experiments show that a variety of network architectures benefit from mutual learning and achieve compelling results on CIFAR-100 recognition and Market-1501 person re-identification benchmarks. Surprisingly, it is revealed that no prior powerful teacher network is necessary -- mutual learning of a collection of simple student networks works, and moreover outperforms distillation from a more powerful yet static teacher. : 10 pages, 4 figures