相关论文: Exploring and Distilling Posterior and Prior Knowl…

Large Language Models (LLMs) can transfer their reasoning skills to smaller models by teaching them to generate the intermediate reasoning process required to solve multistep reasoning tasks. While LLMs can accurately solve reasoning tasks…

Radiology Report Generation (RRG) is essential for computer-aided diagnosis and medication guidance, which can relieve the heavy burden of radiologists by automatically generating the corresponding radiology reports according to the given…

The popularity of multimodal sensors and the accessibility of the Internet have brought us a massive amount of unlabeled multimodal data. Since existing datasets and well-trained models are primarily unimodal, the modality gap between a…

Recently, machine unlearning approaches have been proposed to remove sensitive information from well-trained large models. However, most existing methods are tailored for LLMs, while MLLM-oriented unlearning remains at its early stage.…

Despite the recent works on knowledge distillation (KD) have achieved a further improvement through elaborately modeling the decision boundary as the posterior knowledge, their performance is still dependent on the hypothesis that the…

Recent advances in knowledge distillation (KD) predominantly emphasize feature-level knowledge transfer, frequently overlooking critical information embedded within the teacher's logit distributions. In this paper, we revisit logit-based…

Knowledge distillation learns a lightweight student model that mimics a cumbersome teacher. Existing methods regard the knowledge as the feature of each instance or their relations, which is the instance-level knowledge only from the…

The accurate segmentation of medical images is a crucial step in obtaining reliable morphological statistics. However, training a deep neural network for this task requires a large amount of labeled data to ensure high-accuracy results. To…

This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation. Directly employing previous distillation approaches yields inferior results due to the…

On many natural language processing tasks, large pre-trained language models (PLMs) have shown overwhelming performances compared with traditional neural network methods. Nevertheless, their huge model size and low inference speed have…

Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their…

Pretrained Language Models (PLMs) store extensive knowledge within their weights, enabling them to recall vast amount of information. However, relying on this parametric knowledge brings some limitations such as outdated information or gaps…

Automating report generation for medical imaging promises to reduce workload and assist diagnosis in clinical practice. Recent work has shown that deep learning models can successfully caption natural images. However, learning from medical…

Although deep convolution neural networks (DCNN) have achieved excellent performance in human pose estimation, these networks often have a large number of parameters and computations, leading to the slow inference speed. For this issue, an…

The success of deep convolutional neural networks is partially attributed to the massive amount of annotated training data. However, in practice, medical data annotations are usually expensive and time-consuming to be obtained. Considering…

Understanding visual relationships involves identifying the subject, the object, and a predicate relating them. We leverage the strong correlations between the predicate and the (subj,obj) pair (both semantically and spatially) to predict…

Many medical image segmentation methods have achieved impressive results. Yet, most existing methods do not take into account the shape-intensity prior information. This may lead to implausible segmentation results, in particular for images…

Large Language Models (LLMs) face significant challenges at inference time due to their high computational demands. To address this, we present Performance-Guided Knowledge Distillation (PGKD), a cost-effective and high-throughput solution…

Large language models (LLMs) have demonstrated remarkable capabilities in various domains, including radiology report generation. Previous approaches have attempted to utilize multimodal LLMs for this task, enhancing their performance…

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…