相关论文: Knowledge Extraction and Distillation from Large-S…

In practical applications of human pose estimation, low-resolution inputs frequently occur, and existing state-of-the-art models perform poorly with low-resolution images. This work focuses on boosting the performance of low-resolution…

We propose Cross-Attention-based Non-local Knowledge Distillation (CanKD), a novel feature-based knowledge distillation framework that leverages cross-attention mechanisms to enhance the knowledge transfer process. Unlike traditional…

The extensive amounts of data required for training deep neural networks pose significant challenges on storage and transmission fronts. Dataset distillation has emerged as a promising technique to condense the information of massive…

Segmentation maps of medical images annotated by medical experts contain rich spatial information. In this paper, we propose to decompose annotation maps to learn disentangled and richer feature transforms for segmentation problems in…

The popularity of large-scale pre-training has promoted the development of medical foundation models. However, some studies have shown that although foundation models exhibit strong general feature extraction capabilities, their performance…

Accurate instrument segmentation in endoscopic vision of robot-assisted surgery is challenging due to reflection on the instruments and frequent contacts with tissue. Deep neural networks (DNN) show competitive performance and are in favor…

Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning process of student…

Knowledge distillation (KD) methods are pivotal in compressing large pre-trained language models into smaller models, ensuring computational efficiency without significantly dropping performance. Traditional KD techniques assume homogeneity…

In recent years, deep convolutional neural networks have made significant advances in pathology image segmentation. However, pathology image segmentation encounters with a dilemma in which the higher-performance networks generally require…

This paper presents a novel supervised convolutional neural network architecture, "DUCK-Net", capable of effectively learning and generalizing from small amounts of medical images to perform accurate segmentation tasks. Our model utilizes…

In this work, we explore data augmentations for knowledge distillation on semantic segmentation. To avoid over-fitting to the noise in the teacher network, a large number of training examples is essential for knowledge distillation.…

Endoscopic depth estimation is a critical technology for improving the safety and precision of minimally invasive surgery. It has attracted considerable attention from researchers in medical imaging, computer vision, and robotics. Over the…

Multimodal dataset distillation aims to synthesize a small set of image-text pairs that enables efficient training of large-scale vision-language models. While dataset distillation has shown promise in unimodal tasks, extending it to…

Multilingual text-video retrieval methods have improved significantly in recent years, but the performance for other languages lags behind English. We propose a Cross-Lingual Cross-Modal Knowledge Distillation method to improve multilingual…

Over the last few decades, artificial intelligence research has made tremendous strides, but it still heavily relies on fixed datasets in stationary environments. Continual learning is a growing field of research that examines how AI…

Automated colonoscopy reporting holds great potential for enhancing quality control and improving cost-effectiveness of colonoscopy procedures. A major challenge lies in the automated identification, tracking, and re-association (ReID) of…

Transformer-based encoder-decoder models have achieved remarkable success in image-to-image transfer tasks, particularly in image restoration. However, their high computational complexity-manifested in elevated FLOPs and parameter…

It has been revealed that efficient dense image prediction (EDIP) models designed for AI chips, trained using the knowledge distillation (KD) framework, encounter two key challenges, including \emph{maintaining boundary region completeness}…

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies…

Data-free knowledge distillation (DFKD) has emerged as a pivotal technique in the domain of model compression, substantially reducing the dependency on the original training data. Nonetheless, conventional DFKD methods that employ…