Refine Myself by Teaching Myself : Feature Refinement via Self-Knowledge Distillation
- Conference Name
- Conference on Computer Vision and Pattern Recognition (CVPR 2021)
- Presentation Date
- Jun 19-25
- City
- Virtual Conference
- File
- cvpr_final.pdf (5.6M) 32time download DATE : 2023-11-09 21:12:15
Mingi Ji, Seungjae Shin, Seunghyun Hwang, Gibeom Park, and Il-Chul Moon. Refine Myself by Teaching Myself : Feature Refinement via Self-Knowledge Distillation. Conference on Computer Vision and Pattern Recognition (CVPR 2021), Virtual Conference, Jun 19-25, 2021 (acceptance rate: 27%)
Abstract
Knowledge distillation is a method of transferring the knowledge from a pretrained complex teacher model to a student model, so a smaller network can replace a large teacher network at the deployment stage. To reduce the necessity of training a large teacher model, the recent literatures introduced a self-knowledge distillation, which trains a student network progressively to distill its own knowledge without a pretrained teacher network. While Self-knowledge distillation is largely divided into a data augmentation based approach and an auxiliary network based approach, the data augmentation approach looses its local information in the augmentation process, which hinders its applicability to diverse vision tasks, such as semantic segmentation. Moreover, these knowledge distillation approaches do not receive the refined feature maps, which are prevalent in the object detection and semantic segmentation community. This paper proposes a novel self-knowledge distillation method, Feature Refinement via Self-Knowledge Distillation (FRSKD), which utilizes an auxiliary self-teacher network to transfer a refined knowledge for the classifier network. Our proposed method, FRSKD, can utilize both soft label and feature-map distillations for the self-knowledge distillation. Therefore, FRSKD can be applied to classification, and semantic segmentation, which emphasize preserving the local information. We demonstrate the effectiveness of FRSKD by enumerating its performance improvements in diverse tasks and benchmark datasets. The implemented code will be open-sourced.
@inproceedings{ji2021refine,
title={Refine myself by teaching myself: Feature refinement via self-knowledge distillation},
author={Ji, Mingi and Shin, Seungjae and Hwang, Seunghyun and Park, Gibeom and Moon, Il-Chul},
booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
pages={10664--10673},
year={2021}
}
Source Website: