相关论文: TSAK: Two-Stage Semantic-Aware Knowledge Distillat…

State-of-the-art results in deep learning have been improving steadily, in good part due to the use of larger models. However, widespread use is constrained by device hardware limitations, resulting in a substantial performance gap between…

Knowledge distillation (KD) has the potential to accelerate MARL by employing a centralized teacher for decentralized students but faces key bottlenecks. Specifically, there are (1) challenges in synthesizing high-performing teaching…

Human Activity Recognition (HAR) is a key building block of many emerging applications such as intelligent mobility, sports analytics, ambient-assisted living and human-robot interaction. With robust HAR, systems will become more…

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,…

Detecting human actions is a crucial task for autonomous robots and vehicles, often requiring the integration of various data modalities for improved accuracy. In this study, we introduce a novel approach to Human Action Recognition (HAR)…

As a fundamental problem, numerous methods are dedicated to the optimization of signal-to-interference-plus-noise ratio (SINR), in a multi-user setting. Although traditional model-based optimization methods achieve strong performance, the…

Autonomous driving systems rely on panoptic perception to jointly handle object detection, drivable area segmentation, and lane line segmentation. Although multi-task learning is an effective way to integrate these tasks, its increasing…

Human Activity Recognition (HAR) is an attractive topic to perceive human behavior and supplying assistive services. Besides the classical inertial unit and vision-based HAR methods, new sensing technologies, such as ultrasound and…

Human Activity Recognition (HAR) with different sensing modalities requires both strong generalization across diverse users and efficient personalization for individuals. However, conventional HAR models often fail to generalize when faced…

Knowledge distillation is one of the most effective methods for model compression. Previous studies have focused on the student model effectively training the predictive distribution of the teacher model. However, during training, the…

Knowledge distillation (KD) has traditionally relied on a static teacher-student framework, where a large, well-trained teacher transfers knowledge to a single student model. However, these approaches often suffer from knowledge…

Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism trade-off, where increasing tokens per forward (TPF) often degrades generation quality.…

Wearable computing and context awareness are the focuses of study in the field of artificial intelligence recently. One of the most appealing as well as challenging applications is the Human Activity Recognition (HAR) utilizing smart…

Knowledge Distillation (KD) has emerged as a crucial technique for compressing Large Language Models (LLMs). Although existing cross-tokenizer KD methods have made notable progress, their effectiveness remains constrained by suboptimal…

Knowledge Distillation (KD) has emerged as a pivotal technique for neural network compression and performance enhancement. Most KD methods aim to transfer dark knowledge from a cumbersome teacher model to a lightweight student model based…

Human activity understanding is crucial for building automatic intelligent system. With the help of deep learning, activity understanding has made huge progress recently. But some challenges such as imbalanced data distribution, action…

Representation knowledge distillation aims at transferring rich information from one model to another. Common approaches for representation distillation mainly focus on the direct minimization of distance metrics between the models'…

Knowledge distillation is widely adopted in semantic segmentation to reduce the computation cost.The previous knowledge distillation methods for semantic segmentation focus on pixel-wise feature alignment and intra-class feature variation…

Large language models (LLMs) have achieved remarkable performance across diverse domains, yet their enormous computational and memory requirements hinder deployment in resource-constrained environments. Knowledge distillation offers a…

Federated Learning has emerged as a promising paradigm for collaborative machine learning, while preserving user data privacy. Despite its potential, standard FL lacks support for diverse heterogeneous device prototypes, which vary…