Related papers: Deep Face Recognition Model Compression via Knowle…
Knowledge distillation (KD) is an effective tool for compressing deep classification models for edge devices. However, the performance of KD is affected by the large capacity gap between the teacher and student networks. Recent methods have…
This paper presents a new state-of-the-art for document image classification and retrieval, using features learned by deep convolutional neural networks (CNNs). In object and scene analysis, deep neural nets are capable of learning a…
In real applications, different computation-resource devices need different-depth networks (e.g., ResNet-18/34/50) with high-accuracy. Usually, existing methods either design multiple networks and train them independently, or construct…
Deep convolutional neural networks (CNNs) have greatly improved the Face Recognition (FR) performance in recent years. Almost all CNNs in FR are trained on the carefully labeled datasets containing plenty of identities. However, such…
While depth tends to improve network performances, it also makes gradient-based training more difficult since deeper networks tend to be more non-linear. The recently proposed knowledge distillation approach is aimed at obtaining small and…
Model compression is a critical area of research in deep learning, in particular in vision, driven by the need to lighten models memory or computational footprints. While numerous methods for model compression have been proposed, most focus…
In this report, we present a new face detection scheme using deep learning and achieve the state-of-the-art detection performance on the well-known FDDB face detetion benchmark evaluation. In particular, we improve the state-of-the-art…
Real-world imagery is often characterized by a significant imbalance of the number of images per class, leading to long-tailed distributions. An effective and simple approach to long-tailed visual recognition is to learn feature…
Model compression has emerged as an important area of research for deploying deep learning models on Internet-of-Things (IoT). However, for extremely memory-constrained scenarios, even the compressed models cannot fit within the memory of a…
This paper presents a novel knowledge distillation neural architecture leveraging efficient transformer networks for effective image classification. Natural images display intricate arrangements encompassing numerous extraneous elements.…
Face recognition in the wild is now advancing towards light-weight models, fast inference speed and resolution-adapted capability. In this paper, we propose a bridge distillation approach to turn a complex face model pretrained on private…
Convolutional neural networks have been widely deployed in various application scenarios. In order to extend the applications' boundaries to some accuracy-crucial domains, researchers have been investigating approaches to boost accuracy…
In recent years, knowledge graph completion (KGC) models based on pre-trained language model (PLM) have shown promising results. However, the large number of parameters and high computational cost of PLM models pose challenges for their…
Pre-trained language models have been applied to various NLP tasks with considerable performance gains. However, the large model sizes, together with the long inference time, limit the deployment of such models in real-time applications.…
We propose a novel knowledge distillation approach, CustomKD, that effectively leverages large vision foundation models (LVFMs) to enhance the performance of edge models (e.g., MobileNetV3). Despite recent advancements in LVFMs, such as…
This paper is aimed at creating extremely small and fast convolutional neural networks (CNN) for the problem of facial expression recognition (FER) from frontal face images. To this end, we employed the popular knowledge distillation (KD)…
Several methods of knowledge distillation have been developed for neural network compression. While they all use the KL divergence loss to align the soft outputs of the student model more closely with that of the teacher, the various…
This paper has proposed a new baseline deep learning model of more benefits for image classification. Different from the convolutional neural network(CNN) practice where filters are trained by back propagation to represent different…
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…
This paper proposes a novel image segmentation approachthat integrates fully convolutional networks (FCNs) with a level setmodel. Compared with a FCN, the integrated method can incorporatesmoothing and prior information to achieve an…