Related papers: Visualizing the embedding space to explain the eff…
Real-time visual localization often utilizes online computing, for which query images or videos are transmitted to remote servers for visual place recognition (VPR). However, limited network bandwidth necessitates image-quality reduction…
Knowledge distillation addresses the problem of transferring knowledge from a teacher model to a student model. In this process, we typically have multiple types of knowledge extracted from the teacher model. The problem is to make full use…
Boosting the task accuracy of tiny neural networks (TNNs) has become a fundamental challenge for enabling the deployments of TNNs on edge devices which are constrained by strict limitations in terms of memory, computation, bandwidth, and…
Knowledge distillation has become one of the most important model compression techniques by distilling knowledge from larger teacher networks to smaller student ones. Although great success has been achieved by prior distillation methods…
Reviewing plays an important role when learning knowledge. The knowledge acquisition at a certain time point may be strongly inspired with the help of previous experience. Thus the knowledge growing procedure should show strong relationship…
In self-supervised learning, self-distilled methods have shown impressive performance, learning representations useful for downstream tasks and even displaying emergent properties. However, state-of-the-art methods usually rely on ensembles…
The task of accelerating large neural networks on general purpose hardware has, in recent years, prompted the use of channel pruning to reduce network size. However, the efficacy of pruning based approaches has since been called into…
Knowledge distillation has emerged as an effective strategy for compressing large language models' (LLMs) knowledge into smaller, more efficient student models. However, standard one-shot distillation methods often produce suboptimal…
High-quality computer vision models typically address the problem of understanding the general distribution of real-world images. However, most cameras observe only a very small fraction of this distribution. This offers the possibility of…
Optimizing neural networks with noisy labels is a challenging task, especially if the label set contains real-world noise. Networks tend to generalize to reasonable patterns in the early training stages and overfit to specific details of…
Deep learning based models are relatively large, and it is hard to deploy such models on resource-limited devices such as mobile phones and embedded devices. One possible solution is knowledge distillation whereby a smaller model (student…
Knowledge distillation is a popular paradigm for learning portable neural networks by transferring the knowledge from a large model into a smaller one. Most existing approaches enhance the student model by utilizing the similarity…
Efficient models for remote sensing object counting are urgently required for applications in scenarios with limited computing resources, such as drones or embedded systems. A straightforward yet powerful technique to achieve this is…
The outpouring of various pre-trained models empowers knowledge distillation by providing abundant teacher resources, but there lacks a developed mechanism to utilize these teachers adequately. With a massive model repository composed of…
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…
Deep learning methods usually require a large amount of training data and lack interpretability. In this paper, we propose a novel knowledge distillation and model interpretation framework for medical image classification that jointly…
Knowledge distillation (KD) is a valuable technique for compressing large deep learning models into smaller, edge-suitable networks. However, conventional KD frameworks rely on pre-trained high-capacity teacher networks, which introduce…
The problem of learning from few labeled examples while using large amounts of unlabeled data has been approached by various semi-supervised methods. Although these methods can achieve superior performance, the models are often not…
Knowledge distillation describes a method for training a student network to perform better by learning from a stronger teacher network. Translating a sentence with an Neural Machine Translation (NMT) engine is time expensive and having a…
Traditional one-shot medical image segmentation (MIS) methods use registration networks to propagate labels from a reference atlas or rely on comprehensive sampling strategies to generate synthetic labeled data for training. However, these…