相关论文: Ensemble diverse hypotheses and knowledge distilla…

Deep learning models, particularly recurrent neural networks and their variants, such as long short-term memory, have significantly advanced time series data analysis. These models capture complex, sequential patterns in time series,…

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…

We propose a hypothesis disparity regularized mutual information maximization~(HDMI) approach to tackle unsupervised hypothesis transfer -- as an effort towards unifying hypothesis transfer learning (HTL) and unsupervised domain adaptation…

Existing techniques often attempt to make knowledge transfer from a powerful machine translation (MT) to speech translation (ST) model with some elaborate techniques, which often requires transcription as extra input during training.…

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…

Collaborative fairness is a crucial challenge in federated learning. However, existing approaches often overlook a practical yet complex form of heterogeneity: imbalanced covariate shift. We provide a theoretical analysis of this setting,…

Recently, Bird's-Eye-View (BEV) representation has gained increasing attention in multi-view 3D object detection, which has demonstrated promising applications in autonomous driving. Although multi-view camera systems can be deployed at low…

Point-cloud based 3D object detectors recently have achieved remarkable progress. However, most studies are limited to the development of network architectures for improving only their accuracy without consideration of the computational…

Expanding visual categorization into a novel domain without the need of extra annotation has been a long-term interest for multimedia intelligence. Previously, this challenge has been approached by unsupervised domain adaptation (UDA).…

Transformer-based detectors (DETRs) are becoming popular for their simple framework, but the large model size and heavy time consumption hinder their deployment in the real world. While knowledge distillation (KD) can be an appealing…

As a special type of multimedia data, Lithography Hotspot Detection (LHD) training often requires stronger privacy protection than conventional multimedia data, and federated learning provides a promising potential solution to this…

We propose ClassroomKD, a novel multi-mentor knowledge distillation framework inspired by classroom environments to enhance knowledge transfer between the student and multiple mentors with different knowledge levels. Unlike traditional…

Numerical approximation methods for the Koopman operator have advanced considerably in the last few years. In particular, data-driven approaches such as dynamic mode decomposition (DMD) and its generalization, the extended-DMD (EDMD), are…

Semi-supervised domain adaptation (SSDA) aims to solve tasks in target domain by utilizing transferable information learned from the available source domain and a few labeled target data. However, source data is not always accessible in…

Knowledge distillation (KD) involves transferring knowledge from a pre-trained heavy teacher model to a lighter student model, thereby reducing the inference cost while maintaining comparable effectiveness. Prior KD techniques typically…

Deep Learning has emerged as a promising approach for skin lesion analysis. However, existing methods mostly rely on fully supervised learning, requiring extensive labeled data, which is challenging and costly to obtain. To alleviate this…

Recently Data-Free Knowledge Distillation (DFKD) has garnered attention and can transfer knowledge from a teacher neural network to a student neural network without requiring any access to training data. Although diffusion models are adept…

Knowledge distillation (KD) aims at improving the performance of a compact student model by distilling the knowledge from a high-performing teacher model. In this paper, we present an adaptive KD approach, namely AdaDistill, for deep face…

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…

3D object detection is one of the fundamental perception tasks for autonomous vehicles. Fulfilling such a task with a 4D millimeter-wave radar is very attractive since the sensor is able to acquire 3D point clouds similar to Lidar while…