相关论文: Knowledge Distillation Circumvents Nonlinearity fo…

Distributed learning frameworks often rely on exchanging model parameters across workers, instead of revealing their raw data. A prime example is federated learning that exchanges the gradients or weights of each neural network model. Under…

Spatial and spectral approaches are two major approaches for image processing tasks such as image classification and object recognition. Among many such algorithms, convolutional neural networks (CNNs) have recently achieved significant…

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…

Age-related macular degeneration (AMD) and choroidal neovascularization (CNV)-related conditions are leading causes of vision loss worldwide, with optical coherence tomography (OCT) serving as a cornerstone for early detection and…

Knowledge distillation (KD) has shown great potential for transferring knowledge from a complex teacher model to a simple student model in which the heavy learning task can be accomplished efficiently and without losing too much prediction…

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 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…

Convolutional neural networks (CNNs) define the current state-of-the-art for image recognition. With their emerging popularity, especially for critical applications like medical image analysis or self-driving cars, confirmability is…

Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…

Radiation therapy (RT) is widely employed in the clinic for the treatment of head and neck (HaN) cancers. An essential step of RT planning is the accurate segmentation of various organs-at-risks (OARs) in HaN CT images. Nevertheless,…

Knowledge Distillation (KD) aims at transferring knowledge from a larger well-optimized teacher network to a smaller learnable student network.Existing KD methods have mainly considered two types of knowledge, namely the individual…

Typically, the deployment of face recognition models in the wild needs to identify low-resolution faces with extremely low computational cost. To address this problem, a feasible solution is compressing a complex face model to achieve…

Interests in digital image processing are growing enormously in recent decades. As a result, different data compression techniques have been proposed which are concerned mostly with the minimization of information used for the…

Computer vision often uses highly accurate Convolutional Neural Networks (CNNs), but these deep learning models are associated with ever-increasing energy and computation requirements. Producing more energy-efficient CNNs often requires…

Knowledge distillation (KD) has been widely applied in semantic segmentation to compress large models, but conventional approaches primarily preserve in-domain accuracy while neglecting out-of-domain generalization, which is essential under…

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…

Deep learning networks have achieved state-of-the-art accuracies on computer vision workloads like image classification and object detection. The performant systems, however, typically involve big models with numerous parameters. Once…

While Convolutional Neural Networks (CNNs) excel at learning complex latent-space representations, their over-parameterization can lead to overfitting and reduced performance, particularly with limited data. This, alongside their high…

Discrete Fourier transforms provide a significant speedup in the computation of convolutions in deep learning. In this work, we demonstrate that, beyond its advantages for efficient computation, the spectral domain also provides a powerful…

Convolutions are the core operation of deep learning applications based on Convolutional Neural Networks (CNNs). Current GPU architectures are highly efficient for training and deploying deep CNNs, and hence, these are largely used in…