Related papers: Compact CNN Structure Learning by Knowledge Distil…
Convolutional Neural Networks (CNNs) are prone to overfit small training datasets. We present a novel two-phase pipeline that leverages self-supervised learning and knowledge distillation to improve the generalization ability of CNN models…
Deep learning techniques have been demonstrated to surpass preceding cutting-edge machine learning techniques in recent years, with computer vision being one of the most prominent examples. However, deep learning models suffer from…
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…
Channel pruning and tensor decomposition have received extensive attention in convolutional neural network compression. However, these two techniques are traditionally deployed in an isolated manner, leading to significant accuracy drop…
Knowledge distillation constitutes a potent methodology for condensing substantial neural networks into more compact and efficient counterparts. Within this context, softmax regression representation learning serves as a widely embraced…
Network pruning and knowledge distillation are two widely-known model compression methods that efficiently reduce computation cost and model size. A common problem in both pruning and distillation is to determine compressed architecture,…
It is challenging to bridge the performance gap between Binary CNN (BCNN) and Floating point CNN (FCNN). We observe that, this performance gap leads to substantial residuals between intermediate feature maps of BCNN and FCNN. To minimize…
This paper investigates the piracy problem of deep learning models. Designing and training a well-performing model is generally expensive. However, when releasing them, attackers may reverse engineer the models and pirate their design. This…
This paper presents a novel knowledge distillation based model compression framework consisting of a student ensemble. It enables distillation of simultaneously learnt ensemble knowledge onto each of the compressed student models. Each…
In this work, we consider transferring the structure information from large networks to compact ones for dense prediction tasks in computer vision. Previous knowledge distillation strategies used for dense prediction tasks often directly…
What does a neural network learn when training from a task-specific dataset? Synthesizing this knowledge is the central idea behind Dataset Distillation, which recent work has shown can be used to compress large datasets into a small set of…
Knowledge distillation, which involves extracting the "dark knowledge" from a teacher network to guide the learning of a student network, has emerged as an essential technique for model compression and transfer learning. Unlike previous…
Recently, deep convolutional neural networks (CNNs) have achieved many eye-catching results. However, deploying CNNs on resource-constrained edge devices is constrained by limited memory bandwidth for transmitting large intermediated data…
In this paper we propose a novel decomposition method based on filter group approximation, which can significantly reduce the redundancy of deep convolutional neural networks (CNNs) while maintaining the majority of feature representation.…
We propose a scalable tensorization framework for neural network compression based on slice-wise feature distillation. Unlike conventional tensor decomposition methods that rely on costly global finetuning, our approach decomposes the…
Model compression becomes a recent trend due to the requirement of deploying neural networks on embedded and mobile devices. Hence, both accuracy and efficiency are of critical importance. To explore a balance between them, a knowledge…
Knowledge distillation is an effective method for training small and efficient deep learning models. However, the efficacy of a single method can degenerate when transferring to other tasks, modalities, or even other architectures. To…
Deep neural networks (DNNs) have proven to be effective models for accurate Memory Access Prediction (MAP), a critical task in mitigating memory latency through data prefetching. However, existing DNN-based MAP models suffer from the…
Neural Architecture Search (NAS) has been pivotal in finding optimal network configurations for Convolution Neural Networks (CNNs). While many methods explore NAS from a global search-space perspective, the employed optimization schemes…
Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of…