本论文提出的算法关系知识蒸馏(RKD)迁移教师模型得到的输出结果间的结构化关系给学生模型,不同于之前的只关注个体输出结果,RKD 算法使用两种损失函数:二阶的距离损失(distance-wise)和三阶的角度损失(angle-wise)。在最终计算蒸馏损失函数的时候,同时考虑 KD loss 和 RKD loss。最终精度优于单独使用 KD loss 蒸馏得到的模型精度。
[1] Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network[J]. arXiv preprint arXiv:1503.02531, 2015.
[2] Bagherinezhad H, Horton M, Rastegari M, et al. Label refinery: Improving imagenet classification through label progression[J]. arXiv preprint arXiv:1805.02641, 2018.
[3] Yalniz I Z, Jégou H, Chen K, et al. Billion-scale semi-supervised learning for image classification[J]. arXiv preprint arXiv:1905.00546, 2019.
[4] Cubuk E D, Zoph B, Mane D, et al. Autoaugment: Learning augmentation strategies from data[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2019: 113-123.
[5] Touvron H, Vedaldi A, Douze M, et al. Fixing the train-test resolution discrepancy[C]//Advances in Neural Information Processing Systems. 2019: 8250-8260.
[6] Cui C, Guo R, Du Y, et al. Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones[J]. arXiv preprint arXiv:2103.05959, 2021.
[7] Zhang Y, Xiang T, Hospedales T M, et al. Deep mutual learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 4320-4328.
[8] Heo B, Kim J, Yun S, et al. A comprehensive overhaul of feature distillation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019: 1921-1930.
[9] Du Y, Li C, Guo R, et al. PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System[J]. arXiv preprint arXiv:2109.03144, 2021.
[10] Park W, Kim D, Lu Y, et al. Relational knowledge distillation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 3967-3976.