Related papers: CAE-DFKD: Bridging the Transferability Gap in Data…

Knowledge distillation (KD) provides an effective way to improve the performance of a student network under the guidance of pre-trained teachers. However, this approach usually brings in a large capacity gap between teacher and student…

Knowledge distillation (KD) has been actively studied for image classification tasks in deep learning, aiming to improve the performance of a student based on the knowledge from a teacher. However, applying KD in image regression with a…

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…

Large-scale pre-training has been proven to be crucial for various computer vision tasks. However, with the increase of pre-training data amount, model architecture amount, and the private/inaccessible data, it is not very efficient or…

Data-free knowledge distillation is able to utilize the knowledge learned by a large teacher network to augment the training of a smaller student network without accessing the original training data, avoiding privacy, security, and…

Federated Knowledge Graph Embedding (FKGE) aims to facilitate collaborative learning of entity and relation embeddings from distributed Knowledge Graphs (KGs) across multiple clients, while preserving data privacy. Training FKGE models with…

Knowledge distillation (KD) is an effective model compression technique that transfers knowledge from a high-performance teacher to a lightweight student, reducing computational and storage costs while maintaining competitive accuracy.…

Knowledge Distillation (KD) has made remarkable progress in the last few years and become a popular paradigm for model compression and knowledge transfer. However, almost all existing KD algorithms are data-driven, i.e., relying on a large…

Knowledge distillation (KD) is an efficient approach to transfer the knowledge from a large "teacher" network to a smaller "student" network. Traditional KD methods require lots of labeled training samples and a white-box teacher…

Knowledge distillation (KD) has shown very promising capabilities in transferring learning representations from large models (teachers) to small models (students). However, as the capacity gap between students and teachers becomes larger,…

Data-free knowledge distillation (DFKD) transfers knowledge from a teacher to a student without access to the real in-distribution (ID) data. While existing methods perform well on small-scale images, they suffer from mode collapse when…

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…

Knowledge Distillation (KD) is a popular technique to transfer knowledge from a teacher model or ensemble to a student model. Its success is generally attributed to the privileged information on similarities/consistency between the class…

Gait recognition is an attractive biometric modality for long-range and contact-free identification, but high-performing gait models often rely on deep and computationally expensive architectures that are difficult to deploy in practice.…

Diffusion models (DMs) have demonstrated exceptional generative capabilities across various domains, including image, video, and so on. A key factor contributing to their effectiveness is the high quantity and quality of data used during…

Knowledge distillation (KD), known for its ability to transfer knowledge from a cumbersome network (teacher) to a lightweight one (student) without altering the architecture, has been garnering increasing attention. Two primary categories…

Previous knowledge distillation methods have shown their impressive performance on model compression tasks, however, it is hard to explain how the knowledge they transferred helps to improve the performance of the student network. In this…

Knowledge distillation deals with the problem of training a smaller model (Student) from a high capacity source model (Teacher) so as to retain most of its performance. Existing approaches use either the training data or meta-data extracted…

Data-free Knowledge Distillation (DFKD) has gained popularity recently, with the fundamental idea of carrying out knowledge transfer from a Teacher neural network to a Student neural network in the absence of training data. However, in the…

Due to privacy or patent concerns, a growing number of large models are released without granting access to their training data, making transferring their knowledge inefficient and problematic. In response, Data-Free Knowledge Distillation…