| Paper ID | MLSP-48.4 |
| Paper Title |
A COMPACT JOINT DISTILLATION NETWORK FOR VISUAL FOOD RECOGNITION |
| Authors |
Heng Zhao, Kim-Hui Yap, Alex Chichung Kot, Nanyang Technological University, Singapore |
| Session | MLSP-48: Neural Network Applications |
| Location | Gather.Town |
| Session Time: | Friday, 11 June, 14:00 - 14:45 |
| Presentation Time: | Friday, 11 June, 14:00 - 14:45 |
| Presentation |
Poster
|
| Topic |
Machine Learning for Signal Processing: [MLR-APPL] Applications of machine learning |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Visual food recognition is emerging as an important application in dietary monitoring and management in recent years. Existing works use large backbone networks to achieve good performance. However, these networks are not able to be deployed on personal portable devices due to large size and computation cost. Some compact networks have been developed, however, their performance are usually lower than the large backbone networks. In view of this, this paper proposes a joint distillation framework that targets to achieve a high visual food recognition accuracy using a compact network. As opposed to the more traditional one-directional knowledge distillation methods, the proposed knowledge distillation framework trains both the large teacher network and the compact student network simultaneously. The framework introduces a new Multi-Layer Distillation (MLD) for simultaneous teacher-student learning at multiple layers of different abstraction. A novel Instance Activation Mapping (IAM) is proposed to jointly train the teacher and student networks using generated instance-level activation map that incorporates label information for each training image. Experimental results on the two benchmark datasets UECFood-256 and Food-101 show that the trained compact student network achieves state-of-the-art performance at 83.5% and 90.4%, respectively, while achieving more than 4 times deduction regarding network model size. |
