Knowledge Distillation in Generations: More Tolerant Teachers Educate Better Students
원문 초록
We focus on the problem of training a deep neural network in generations. The flowchart is that, in order to optimize the target network (student), another network (teacher) with the same architecture is first trained, and used to provide part of supervision signals in the next stage. While this strategy leads to a higher accuracy, many aspects (e.g., why teacher-student optimization helps) still need further explorations. This paper studies this problem from a perspective of controlling the strictness in training the teacher network. Existing approaches mostly used a hard distribution (e.g., one-hot vectors) in training, leading to a strict teacher which itself has a high accuracy, but we argue that the teacher needs to be more tolerant, although this often implies a lower accuracy. The implementation is very easy, with merely an extra loss term added to the teacher network, facilitating a few secondary classes to emerge and complement to the primary class. Consequently, the teacher provides a milder supervision signal (a less peaked distribution), and makes it possible for the student to learn from inter-class similarity and potentially lower the risk of over-fitting. Experiments are performed on standard image classification tasks (CIFAR100 and ILSVRC2012). Although the teacher network behaves less powerful, the students show a persistent ability growth and eventually achieve higher classification accuracies than other competitors. Model ensemble and transfer feature extraction also verify the effectiveness of our approach.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Generative Adversarial Minority Oversampling for Spectral-Spatial Hyperspectral Image Classification
Attention-Based Adaptive Spectral-Spatial Kernel ResNet for Hyperspectral Image Classification
Multi-direction Networks with Attentional Spectral Prior for Hyperspectral Image Classification
Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-Constrained Edge Computing Systems
Beyond the Attention: Distinguish the Discriminative and Confusable Features For Fine-grained Image Classification
Multiscale Context-Aware Ensemble Deep KELM for Efficient Hyperspectral Image Classification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.