Related papers: Frequency-Aligned Knowledge Distillation for Light…
Structured prediction models aim at solving a type of problem where the output is a complex structure, rather than a single variable. Performing knowledge distillation for such models is not trivial due to their exponentially large output…
Knowledge distillation (KD) has been proven to be a simple and effective tool for training compact models. Almost all KD variants for dense prediction tasks align the student and teacher networks' feature maps in the spatial domain,…
We introduce Layered Self-Supervised Knowledge Distillation (LSSKD) framework for training compact deep learning models. Unlike traditional methods that rely on pre-trained teacher networks, our approach appends auxiliary classifiers to…
Existing Knowledge Distillation (KD) methods often align feature information between teacher and student by exploring meaningful feature processing and loss functions. However, due to the difference in feature distributions between the…
Despite the success of Deep Learning (DL), the deployment of modern DL models requiring large computational power poses a significant problem for resource-constrained systems. This necessitates building compact networks that reduce…
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…
In this paper, we propose an intra-set and inter-set recursive fusion framework with time-frequency calibrated knowledge distillation (I$^2$SRF-TFCKD) for SE. Different from previous distillation strategies for SE, the proposed framework…
Deep learning models, particularly recurrent neural networks and their variants, such as long short-term memory, have significantly advanced time series data analysis. These models capture complex, sequential patterns in time series,…
Accurately forecasting the bursty and non-stationary power demand of AI data centers has become increasingly important, as abrupt workload-driven variations at the GPU-node level can affect real-time operational efficiency, power…
Deep cascaded architectures for magnetic resonance imaging (MRI) acceleration have shown remarkable success in providing high-quality reconstruction. However, as the number of cascades increases, the improvements in reconstruction tend to…
This work introduces a novel knowledge distillation framework for classification tasks where information on existing subclasses is available and taken into consideration. In classification tasks with a small number of classes or binary…
In the era of large scale pretrained models, Knowledge Distillation (KD) serves an important role in transferring the wisdom of computationally heavy teacher models to lightweight, efficient student models while preserving performance.…
Camera-based temporal 3D object detection has shown impressive results in autonomous driving, with offline models improving accuracy by using future frames. Knowledge distillation (KD) can be an appealing framework for transferring rich…
Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power consumption, and slower inference, which hinder their…
Efficient real-time traffic prediction is crucial for reducing transportation time. To predict traffic conditions, we employ a spatio-temporal graph neural network (ST-GNN) to model our real-time traffic data as temporal graphs. Despite its…
Knowledge Distillation (KD) compresses neural networks by learning a small network (student) via transferring knowledge from a pre-trained large network (teacher). Many endeavours have been devoted to the image domain, while few works focus…
Beam training and prediction in real-world millimeter-wave (mmWave) communications systems are challenging due to rapidly time-varying channels and strong interference from surrounding objects. In this context, widely available sensors,…
Knowledge distillation is an effective and stable method for model compression via knowledge transfer. Conventional knowledge distillation (KD) is to transfer knowledge from a large and well pre-trained teacher network to a small student…
Knowledge distillation (KD) is known as a promising solution to compress large language models (LLMs) via transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the…
Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we…