Related papers: ScaleKD: Strong Vision Transformers Could Be Excel…

Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…

Knowledge distillation (KD) is a new method for transferring knowledge of a structure under training to another one. The typical application of KD is in the form of learning a small model (named as a student) by soft labels produced by a…

Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…

Vision transformer (ViT) recently has drawn great attention in computer vision due to its remarkable model capability. However, most prevailing ViT models suffer from huge number of parameters, restricting their applicability on devices…

This paper discusses four facets of the Knowledge Distillation (KD) process for Convolutional Neural Networks (CNNs) and Vision Transformer (ViT) architectures, particularly when executed on edge devices with constrained processing…

Many recent breakthroughs in machine learning have been enabled by the pre-trained foundation models. By scaling up model parameters, training data, and computation resources, foundation models have significantly advanced the…

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,…

Knowledge distillation (KD) has emerged as a promising technique in deep learning, typically employed to enhance a compact student network through learning from their high-performance but more complex teacher variant. When applied in the…

Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due to their computational intensity and inference latency.…

Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student model aligns its output distribution to that of a selected…

Most knowledge distillation (KD) methodologies predominantly focus on teacher-student pairs with similar architectures, such as both being convolutional neural networks (CNNs). However, the potential and flexibility of KD can be greatly…

Masked image modeling (MIM) pre-training for large-scale vision transformers (ViTs) has enabled promising downstream performance on top of the learned self-supervised ViT features. In this paper, we question if the \textit{extremely simple}…

Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model. Previous KD methods typically train a student by minimizing a task-related loss and…

Knowledge distillation (KD) is widely used for training a compact model with the supervision of another large model, which could effectively improve the performance. Previous methods mainly focus on two aspects: 1) training the student to…

Benefiting from well-trained deep neural networks (DNNs), model compression have captured special attention for computing resource limited equipment, especially edge devices. Knowledge distillation (KD) is one of the widely used compression…

Knowledge distillation (KD) is an effective framework to transfer knowledge from a large-scale teacher to a compact yet well-performing student. Previous KD practices for pre-trained language models mainly transfer knowledge by aligning…

With the improvement of AI chips (e.g., GPU, TPU, and NPU) and the fast development of the Internet of Things (IoT), some robust deep neural networks (DNNs) are usually composed of millions or even hundreds of millions of parameters. Such a…

Knowledge distillation (KD) has traditionally relied on a static teacher-student framework, where a large, well-trained teacher transfers knowledge to a single student model. However, these approaches often suffer from knowledge…

Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power consumption, and slower inference, which hinder their…

Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the…