Search

Deep neural networks have achieved a great success in a variety of applications, such as self-driving cars and intelligent robotics. Meanwhile, knowledge distillation has received increasing attention as an effective model compression technique for training very efficient deep models. The performance of the student network obtained through knowledge distillation heavily depends on whether the transfer of the teacher's knowledge can effectively guide the student training. However, most existing knowledge distillation schemes require a large teacher network pre-trained on large-scale data sets, which can increase the difficulty of knowledge distillation in different applications. In this article, we propose a feature fusion-based collaborative learning for knowledge distillation. Specifically, during knowledge distillation, it enables networks to learn from each other using the feature/response-based knowledge in different network layers. We concatenate the features learned by the teacher and the student networks to obtain a more representative feature map for knowledge transfer. In addition, we also introduce a network regularization method to further improve the model performance by providing a positive knowledge during training. Experiments and ablation studies on two widely used data sets demonstrate that the proposed method, feature fusion-based collaborative learning, significantly outperforms recent state-of-the-art knowledge distillation methods. [ABSTRACT FROM AUTHOR]

Knowledge distillation is a promising model compression technique that generally distills the knowledge from a complex teacher model to a lightweight student model. However, the performance gain of a student model is usually limited by the capacity gap between the large teacher model and the small student model. In this paper, we propose a new collaborative knowledge distillation method that makes use of a new strategy, named Filter Knowledge Transfer (FKT) to detect and learn the valuable filter information following from the teacher to the student. To be specific, the useful knowledge of filters measured by using information entropy is transferred between different peer networks and unimportant filters are reactivated according to the ratio based on the characterized filter information entropy during the online distillation process. Experimental results derived on four popular datasets, CIFAR-10/100, Market-1501, and Tiny-ImageNet, demonstrate the superiority of our proposed method over the others we considered. • Design filter knowledge transfer. • Propose a new collaborative knowledge distillation method. • Design filter knowledge entropy to reflect the importance of filter knowledge. [ABSTRACT FROM AUTHOR]

Knowledge distillation (KD) is a widely adopted model compression technique for improving the performance of compact student models, by utilizing the "dark knowledge" of a large teacher model. However, previous studies have not adequately investigated the effectiveness of supervision from the teacher model, and overconfident predictions in the student model may degrade its performance. In this work, we propose a novel framework, Teacher–Student Complementary Sample Contrastive Distillation (TSCSCD), that alleviate these challenges. TSCSCD consists of three key components: Contrastive Sample Hardness (CSH), Supervision Signal Correction (SSC), and Student Self-Learning (SSL). Specifically, CSH evaluates the teacher's supervision for each sample by comparing the predictions of two compact models, one distilled from the teacher and the other trained from scratch. SSC corrects weak supervision according to CSH, while SSL employs integrated learning among multi-classifiers to regularize overconfident predictions. Extensive experiments on four real-world datasets demonstrate that TSCSCD outperforms recent state-of-the-art knowledge distillation techniques. • We present a supervision correction component for knowledge distillation (KD). • We propose a self-learning component that constrains the overconfident prediction. • The effectiveness of framework is evaluated on four real-world datasets. [ABSTRACT FROM AUTHOR]