Related papers: A Dynamic Knowledge Distillation Method Based on t…
Recent Knowledge distillation (KD) studies show that different manually designed schemes impact the learned results significantly. Yet, in KD, automatically searching an optimal distillation scheme has not yet been well explored. In this…
Convolutional neural networks have a significant improvement in the accuracy of Object detection. As convolutional neural networks become deeper, the accuracy of detection is also obviously improved, and more floating-point calculations are…
Deep learning has significantly advanced state-of-the-art of speech recognition in the past few years. However, compared to conventional Gaussian mixture acoustic models, neural network models are usually much larger, and are therefore not…
Resource-constrained perception systems such as edge computing and vision-for-robotics require vision models to be both accurate and lightweight in computation and memory usage. While knowledge distillation is a proven strategy to enhance…
Knowledge distillation as a broad class of methods has led to the development of lightweight and memory efficient models, using a pre-trained model with a large capacity (teacher network) to train a smaller model (student network).…
Quantization and Knowledge distillation (KD) methods are widely used to reduce memory and power consumption of deep neural networks (DNNs), especially for resource-constrained edge devices. Although their combination is quite promising to…
In real applications, different computation-resource devices need different-depth networks (e.g., ResNet-18/34/50) with high-accuracy. Usually, existing methods either design multiple networks and train them independently, or construct…
The large memory and computation consumption in convolutional neural networks (CNNs) has been one of the main barriers for deploying them on resource-limited systems. To this end, most cheap convolutions (e.g., group convolution, depth-wise…
Large-scale visual learning is increasingly limited by training cost. Existing knowledge distillation methods transfer from a stronger teacher to a weaker student for compression or final-accuracy improvement. We instead investigate…
Previous knowledge distillation methods have shown their impressive performance on model compression tasks, however, it is hard to explain how the knowledge they transferred helps to improve the performance of the student network. In this…
We propose a novel knowledge distillation approach to facilitate the transfer of dark knowledge from a teacher to a student. Contrary to most of the existing methods that rely on effective training of student models given pretrained…
Knowledge Distillation is an effective method of transferring knowledge from a large model to a smaller model. Distillation can be viewed as a type of model compression, and has played an important role for on-device ASR applications. In…
Knowledge distillation is a technique used to train a small student network using the output generated by a large teacher network, and has many empirical advantages~\citep{Hinton2015DistillingTK}. While the standard one-shot approach to…
Knowledge distillation (KD) has shown very promising capabilities in transferring learning representations from large models (teachers) to small models (students). However, as the capacity gap between students and teachers becomes larger,…
Existing knowledge distillation (KD) methods have demonstrated their ability in achieving student network performance on par with their teachers. However, the knowledge gap between the teacher and student remains significant and may hinder…
Knowledge distillation (KD) has demonstrated its effectiveness to boost the performance of graph neural networks (GNNs), where its goal is to distill knowledge from a deeper teacher GNN into a shallower student GNN. However, it is actually…
The crux of knowledge distillation is to effectively train a resource-limited student model with the guide of a pre-trained larger teacher model. However, when there is a large difference between the model complexities of teacher and…
Knowledge distillation (KD) is one of the prominent techniques for model compression. In this method, the knowledge of a large network (teacher) is distilled into a model (student) with usually significantly fewer parameters. KD tries to…
Recent advances in deep learning has lead to rapid developments in the field of image retrieval. However, the best performing architectures incur significant computational cost. Recent approaches tackle this issue using knowledge…
This paper explores the use of knowledge distillation to improve a Multi-Task Deep Neural Network (MT-DNN) (Liu et al., 2019) for learning text representations across multiple natural language understanding tasks. Although ensemble learning…