相关论文: Deep Epidemiological Modeling by Black-box Knowled…

Condensed datasets offer a compact representation of larger datasets, but training models directly on them or using them to enhance model performance through knowledge distillation (KD) can result in suboptimal outcomes due to limited…

Diffusion models generate high-quality images through progressive denoising but are computationally intensive due to large model sizes and repeated sampling. Knowledge distillation, which transfers knowledge from a complex teacher to a…

To boost the performance, deep neural networks require deeper or wider network structures that involve massive computational and memory costs. To alleviate this issue, the self-knowledge distillation method regularizes the model by…

Federated learning is widely used to learn intelligent models from decentralized data. In federated learning, clients need to communicate their local model updates in each iteration of model learning. However, model updates are large in…

Knowledge distillation is an effective method to transfer the knowledge from the cumbersome teacher model to the lightweight student model. Online knowledge distillation uses the ensembled prediction results of multiple student models as…

Knowledge distillation is a popular paradigm for learning portable neural networks by transferring the knowledge from a large model into a smaller one. Most existing approaches enhance the student model by utilizing the similarity…

In many situations, we need to build and deploy separate models in related environments with different data qualities. For example, an environment with strong observation equipments (e.g., intensive care units) often provides high-quality…

SARS-CoV2, which causes coronavirus disease (COVID-19) is continuing to spread globally and has become a pandemic. People have lost their lives due to the virus and the lack of counter measures in place. Given the increasing caseload and…

Knowledge Distillation (KD) is a powerful approach for compressing a large model into a smaller, more efficient model, particularly beneficial for latency-sensitive applications like recommender systems. However, current KD research…

Deep pre-training and fine-tuning models (like BERT, OpenAI GPT) have demonstrated excellent results in question answering areas. However, due to the sheer amount of model parameters, the inference speed of these models is very slow. How to…

Benefiting from well-trained deep neural networks (DNNs), model compression have captured special attention for computing resource limited equipment, especially edge devices. Knowledge distillation (KD) is one of the widely used compression…

Deep neural networks often have a huge number of parameters, which posts challenges in deployment in application scenarios with limited memory and computation capacity. Knowledge distillation is one approach to derive compact models from…

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…

Deep metric learning aims to transform input data into an embedding space, where similar samples are close while dissimilar samples are far apart from each other. In practice, samples of new categories arrive incrementally, which requires…

One of the most serious global health threat is COVID-19 pandemic. The emphasis on improving diagnosis and increasing the diagnostic capability helps stopping its spread significantly. Therefore, to assist the radiologist or other medical…

In this paper, a novel confidence conditioned knowledge distillation (CCKD) scheme for transferring the knowledge from a teacher model to a student model is proposed. Existing state-of-the-art methods employ fixed loss functions for this…

In late 2019, COVID-19, a severe respiratory disease, emerged, and since then, the world has been facing a deadly pandemic caused by it. This ongoing pandemic has had a significant effect on different aspects of societies. The uncertainty…

Knowledge Distillation (KD) refers to transferring knowledge from a large model to a smaller one, which is widely used to enhance model performance in machine learning. It tries to align embedding spaces generated from the teacher and the…

In the history of knowledge distillation, the focus has once shifted over time from logit-based to feature-based approaches. However, this transition has been revisited with the advent of Decoupled Knowledge Distillation (DKD), which…

While deep reinforcement learning has achieved promising results in challenging decision-making tasks, the main bones of its success --- deep neural networks are mostly black-boxes. A feasible way to gain insight into a black-box model is…