Related papers: Teach Me to Trick: Exploring Adversarial Transfera…
To reduce the large computation and storage cost of a deep convolutional neural network, the knowledge distillation based methods have pioneered to transfer the generalization ability of a large (teacher) deep network to a light-weight…
Knowledge Distillation (KD) aims to distill the knowledge of a cumbersome teacher model into a lightweight student model. Its success is generally attributed to the privileged information on similarities among categories provided by the…
Deep learning models are shown to be vulnerable to adversarial examples. Though adversarial training can enhance model robustness, typical approaches are computationally expensive. Recent works proposed to transfer the robustness to…
Knowledge Distillation (KD) is a common knowledge transfer algorithm used for model compression across a variety of deep learning based natural language processing (NLP) solutions. In its regular manifestations, KD requires access to the…
Knowledge distillation aims to compress a powerful yet cumbersome teacher model into a lightweight student model without much sacrifice of performance. For this purpose, various approaches have been proposed over the past few years,…
Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher network to strengthen a smaller student. Existing methods focus on excavating the knowledge hints and transferring the whole knowledge to the student. However,…
Achieving resiliency against adversarial attacks is necessary prior to deploying neural network classifiers in domains where misclassification incurs substantial costs, e.g., self-driving cars or medical imaging. Recent work has…
Knowledge Distillation (KD) is a powerful approach for compressing a large model into a smaller, more efficient model, particularly beneficial for latency-sensitive applications like recommender systems. However, current KD research…
Knowledge Distillation (KD) is a widespread technique for compressing the knowledge of large models into more compact and efficient models. KD has proved to be highly effective in building well-performing low-complexity Acoustic Scene…
Knowledge distillation (KD) is widely used for compressing a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, current KD methods for auto-regressive sequence models suffer from…
Knowledge distillation (KD) is a powerful strategy for training deep neural networks (DNNs). Although it was originally proposed to train a more compact "student" model from a large "teacher" model, many recent efforts have focused on…
We present Knowledge Distillation with Meta Learning (MetaDistil), a simple yet effective alternative to traditional knowledge distillation (KD) methods where the teacher model is fixed during training. We show the teacher network can learn…
Modern Natural Language Generation (NLG) models come with massive computational and storage requirements. In this work, we study the potential of compressing them, which is crucial for real-world applications serving millions of users. We…
In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promising results. Despite their remarkable performance…
In recent years the empirical success of transfer learning with neural networks has stimulated an increasing interest in obtaining a theoretical understanding of its core properties. Knowledge distillation where a smaller neural network is…
Knowledge Distillation (KD) utilizes training data as a transfer set to transfer knowledge from a complex network (Teacher) to a smaller network (Student). Several works have recently identified many scenarios where the training data may…
Knowledge distillation (KD) has become an important technique for model compression and knowledge transfer. In this work, we first perform a comprehensive analysis of the knowledge transferred by different KD methods. We demonstrate that…
This paper focuses on an important type of black-box attacks, i.e., transfer-based adversarial attacks, where the adversary generates adversarial examples by a substitute (source) model and utilize them to attack an unseen target model,…
Knowledge distillation has become an important approach to obtain a compact yet effective model. To achieve this goal, a small student model is trained to exploit the knowledge of a large well-trained teacher model. However, due to the…
Knowledge distillation is a popular approach for enhancing the performance of ''student'' models, with lower representational capacity, by taking advantage of more powerful ''teacher'' models. Despite its apparent simplicity and widespread…