Although deep learning algorithms have achieved significant progress in a variety of
domains, they require costly annotations on huge datasets. Self-supervised learning (SSL) …

Abstract Current Knowledge Distillation (KD) methods for semantic segmentation often
guide the student to mimic the teacher's structured information generated from individual …

This paper presents FedX, an unsupervised federated learning framework. Our model learns
unbiased representation from decentralized and heterogeneous local data. It employs a two …

Abstract Unlike the conventional Knowledge Distillation (KD), Self-KD allows a network to
learn knowledge from itself without any guidance from extra networks. This paper proposes …

Self-supervised learning (SSL) has made remarkable progress in visual representation
learning. Some studies combine SSL with knowledge distillation (SSL-KD) to boost the …

Owing to the nature of privacy protection, feder-ated recommender systems (FedRecs) have
garnered increasing interest in the realm of on-device recommender systems. However …

Prompt learning has emerged as a valuable technique in enhancing vision-language
models (VLMs) such as CLIP for downstream tasks in specific domains. Existing work mainly …

Semantic segmentation is a crucial task in remote sensing and has been predominantly
performed using convolutional neural networks (CNNs) for the past decade. Recently …

The teacher-free online Knowledge Distillation (KD) aims to train an ensemble of multiple
student models collaboratively and distill knowledge from each other. Although existing …

Sentence representation learning is a crucial task in natural language processing, as the
quality of learned representations directly influences downstream tasks, such as sentence …