Related papers: Deep Face Recognition Model Compression via Knowle…
Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher. A more useful goal than emulation, yet under-explored, is for the student to learn feature representations that…
Neural network quantization aims to accelerate and trim full-precision neural network models by using low bit approximations. Methods adopting the quantization aware training (QAT) paradigm have recently seen a rapid growth, but are often…
We investigate cross-quality knowledge distillation (CQKD), a knowledge distillation method where knowledge from a teacher network trained with full-resolution images is transferred to a student network that takes as input low-resolution…
Multi-microphone speech enhancement using deep neural networks (DNNs) has significantly progressed in recent years. However, many proposed DNN-based speech enhancement algorithms cannot be implemented on devices with limited hardware…
Fine-grained image labels are desirable for many computer vision applications, such as visual search or mobile AI assistant. These applications rely on image classification models that can produce hundreds of thousands (e.g. 100K) of…
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…
Deep neural networks (DNNs) have improved NLP tasks significantly, but training and maintaining such networks could be costly. Model compression techniques, such as, knowledge distillation (KD), have been proposed to address the issue;…
Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from a high-capacity teacher model to a smaller student model by aligning their output distributions. However, existing methods often underperform in…
Recently, the compression and deployment of powerful deep neural networks (DNNs) on resource-limited edge devices to provide intelligent services have become attractive tasks. Although knowledge distillation (KD) is a feasible solution for…
Vision Transformers (ViTs) have achieved significant advancement in computer vision tasks due to their powerful modeling capacity. However, their performance notably degrades when trained with insufficient data due to lack of inherent…
The deep complex convolution recurrent network (DCCRN) achieves excellent speech enhancement performance by utilizing the audio spectrum's complex features. However, it has a large number of model parameters. We propose a smaller model,…
Deep learning networks are being developed in every stage of the MRI workflow and have provided state-of-the-art results. However, this has come at the cost of increased computation requirement and storage. Hence, replacing the networks…
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,…
Traditional face super-resolution (FSR) methods trained on synthetic datasets usually have poor generalization ability for real-world face images. Recent work has utilized complex degradation models or training networks to simulate the real…
Knowledge distillation aims to enhance the performance of a lightweight student model by exploiting the knowledge from a pre-trained cumbersome teacher model. However, in the traditional knowledge distillation, teacher predictions are only…
Currently, the divergence in distributions of design and operational data, and large computational complexity are limiting factors in the adoption of CNNs in real-world applications. For instance, person re-identification systems typically…
Deep convolutional neural networks (CNN) has become the most promising method for object recognition, repeatedly demonstrating record breaking results for image classification and object detection in recent years. However, a very deep CNN…
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…
In this paper, we propose a feature affinity (FA) assisted knowledge distillation (KD) method to improve quantization-aware training of deep neural networks (DNN). The FA loss on intermediate feature maps of DNNs plays the role of teaching…
Knowledge distillation is an effective method to transfer the knowledge from the cumbersome teacher model to the lightweight student model. Online knowledge distillation uses the ensembled prediction results of multiple student models as…