相关论文: Zero-shot Knowledge Transfer via Adversarial Belie…

Transferring knowledge from a teacher neural network pretrained on the same or a similar task to a student neural network can significantly improve the performance of the student neural network. Existing knowledge transfer approaches match…

Zero-shot learning (ZSL) is made possible by learning a projection function between a feature space and a semantic space (e.g.,~an attribute space). Key to ZSL is thus to learn a projection that is robust against the often large domain gap…

Most existing zero-shot learning approaches exploit transfer learning via an intermediate-level semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no annotation. A…

Recently, zero-shot learning (ZSL) has received increasing interest. The key idea underpinning existing ZSL approaches is to exploit knowledge transfer via an intermediate-level semantic representation which is assumed to be shared between…

Zero-shot domain adaptation (ZSDA) is a category of domain adaptation problems where neither data sample nor label is available for parameter learning in the target domain. With the hypothesis that the shift between a given pair of domains…

Knowledge transfer is shown to be a very successful technique for training neural classifiers: together with the ground truth data, it uses the "privileged information" (PI) obtained by a "teacher" network to train a "student" network. It…

Deep learning and knowledge transfer techniques have permeated the field of medical imaging and are considered as key approaches for revolutionizing diagnostic imaging practices. However, there are still challenges for the successful…

With the success of deep neural networks, knowledge distillation which guides the learning of a small student network from a large teacher network is being actively studied for model compression and transfer learning. However, few studies…

This thesis aims to investigate the feasibility of knowledge transfer between neural networks for medical image segmentation tasks, specifically focusing on the transfer from a larger multi-task "Teacher" network to a smaller "Student"…

Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel training data and…

We consider the few-shot classification task with an unbalanced dataset, in which some classes have sufficient training samples while other classes only have limited training samples. Recent works have proposed to solve this task by…

Recently, zero-shot learning (ZSL) emerged as an exciting topic and attracted a lot of attention. ZSL aims to classify unseen classes by transferring the knowledge from seen classes to unseen classes based on the class description. Despite…

One of important areas of machine learning research is zero-shot learning. It is applied when properly labeled training data set is not available. A number of zero-shot algorithms have been proposed and experimented with. However, none of…

To reduce the overwhelming size of Deep Neural Networks (DNN) teacher-student methodology tries to transfer knowledge from a complex teacher network to a simple student network. We instead propose a novel method called the teacher-class…

Zero-shot learning (ZSL) enables solving a task without the need to see its examples. In this paper, we propose two ZSL frameworks that learn to synthesize parameters for novel unseen classes. First, we propose to cast the problem of ZSL as…

Leveraging class semantic descriptions and examples of known objects, zero-shot learning makes it possible to train a recognition model for an object class whose examples are not available. In this paper, we propose a novel zero-shot…

We propose the task of knowledge distillation detection, which aims to determine whether a student model has been distilled from a given teacher, under a practical setting where only the student's weights and the teacher's API are…

Object recognition systems usually require fully complete manually labeled training data to train the classifier. In this paper, we study the problem of object recognition where the training samples are missing during the classifier…

Achieving resiliency against adversarial attacks is necessary prior to deploying neural network classifiers in domains where misclassification incurs substantial costs, e.g., self-driving cars or medical imaging. Recent work has…

Knowledge distillation (KD) has received much attention due to its success in compressing networks to allow for their deployment in resource-constrained systems. While the problem of adversarial robustness has been studied before in the KD…