相关论文: TTT-KD: Test-Time Training for 3D Semantic Segment…

Causal language models have demonstrated remarkable capabilities, but their size poses significant challenges for deployment in resource-constrained environments. Knowledge distillation, a widely-used technique for transferring knowledge…

Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities. However, current KD methods for auto-regressive…

Prevailing Dataset Distillation (DD) methods leveraging generative models confront two fundamental limitations. First, despite pioneering the use of diffusion models in DD and delivering impressive performance, the vast majority of…

We survey various knowledge distillation (KD) strategies for simple classification tasks and implement a set of techniques that claim state-of-the-art accuracy. Our experiments using standardized model architectures, fixed compute budgets,…

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…

Despite deep neural networks have demonstrated extraordinary power in various applications, their superior performances are at expense of high storage and computational costs. Consequently, the acceleration and compression of neural…

Knowledge Distillation (KD) has emerged as a prominent technique for model compression. However, conventional KD approaches primarily focus on homogeneous architectures with identical tokenizers, constraining their applicability in…

Data-Free Knowledge Distillation (KD) allows knowledge transfer from a trained neural network (teacher) to a more compact one (student) in the absence of original training data. Existing works use a validation set to monitor the accuracy of…

Knowledge distillation aims at transferring knowledge acquired in one model (a teacher) to another model (a student) that is typically smaller. Previous approaches can be expressed as a form of training the student to mimic output…

Reviewing plays an important role when learning knowledge. The knowledge acquisition at a certain time point may be strongly inspired with the help of previous experience. Thus the knowledge growing procedure should show strong relationship…

Transformers are successfully applied to computer vision due to their powerful modeling capacity with self-attention. However, the excellent performance of transformers heavily depends on enormous training images. Thus, a data-efficient…

Knowledge Distillation (KD) is a common knowledge transfer algorithm used for model compression across a variety of deep learning based natural language processing (NLP) solutions. In its regular manifestations, KD requires access to the…

Knowledge distillation (KD) involves transferring knowledge from a pre-trained heavy teacher model to a lighter student model, thereby reducing the inference cost while maintaining comparable effectiveness. Prior KD techniques typically…

Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. The success of KD in auto-regressive language models mainly relies on Reverse KL for mode-seeking and…

This study presents an innovative dynamic weighting knowledge distillation (KD) framework tailored for efficient Earth observation (EO) image classification (IC) in resource-constrained settings. Utilizing EfficientViT and MobileViT as…

The rise of sixth generation (6G) wireless networks promises to deliver ultra-reliable, low-latency, and energy-efficient communications, sensing, and computing. However, traditional centralized artificial intelligence (AI) paradigms are…

To alleviate the expensive human labeling, semi-supervised semantic segmentation employs a few labeled images and an abundant of unlabeled images to predict the pixel-level label map with the same size. Previous methods often adopt…

3D semantic segmentation (3DSS) is an essential process in the creation of a safe autonomous driving system. However, deep learning models for 3D semantic segmentation often suffer from the class imbalance problem and out-of-distribution…

Knowledge distillation aims to enhance the performance of a lightweight student model by exploiting the knowledge from a pre-trained cumbersome teacher model. However, in the traditional knowledge distillation, teacher predictions are only…

Accurate 3D medical image segmentation is vital for diagnosis and treatment planning, but state-of-the-art models are often too large for clinics with limited computing resources. Lightweight architectures typically suffer significant…