Related papers: ShadowTutor: Distributed Partial Distillation for …
Deep learning-based models are at the forefront of most driver observation benchmarks due to their remarkable accuracies but are also associated with high computational costs. This is challenging, as resources are often limited in…
Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train…
Standard Latent Diffusion Models rely on a complex, three-part architecture consisting of a separate encoder, decoder, and diffusion network, which are trained in multiple stages. This modular design is computationally inefficient, leads to…
New intelligence applications are driving increasing interest in deploying deep neural networks (DNN) in a distributed way. To set up distributed deep learning involves alterations of a great number of the parameter configurations of…
Knowledge distillation (KD) compresses deep neural networks by transferring task-related knowledge from cumbersome pre-trained teacher models to compact student models. However, current KD methods for super-resolution (SR) networks overlook…
Knowledge distillation deals with the problem of training a smaller model (Student) from a high capacity source model (Teacher) so as to retain most of its performance. Existing approaches use either the training data or meta-data extracted…
Integrating the structural inductive biases of Graph Neural Networks (GNNs) with the global contextual modeling capabilities of Transformers represents a pivotal challenge in graph representation learning. While GNNs excel at capturing…
Unsupervised video segmentation is a challenging computer vision task, especially due to the lack of supervisory signals coupled with the complexity of visual scenes. To overcome this challenge, state-of-the-art models based on slot…
While deep models have proved successful in learning rich knowledge from massive well-annotated data, they may pose a privacy leakage risk in practical deployment. It is necessary to find an effective trade-off between high utility and…
The human brain has the ability to carry out new tasks with limited experience. It utilizes prior learning experiences to adapt the solution strategy to new domains. On the other hand, deep neural networks (DNNs) generally need large…
Spiking Neural Networks (SNNs) are emerging as a brain-inspired alternative to traditional Artificial Neural Networks (ANNs), prized for their potential energy efficiency on neuromorphic hardware. Despite this, SNNs often suffer from…
Knowledge distillation is the process of transferring the knowledge from a large model to a small model. In this process, the small model learns the generalization ability of the large model and retains the performance close to that of the…
The soaring demand for intelligent mobile applications calls for deploying powerful deep neural networks (DNNs) on mobile devices. However, the outstanding performance of DNNs notoriously relies on increasingly complex models, which in turn…
This paper tackles the problem of semi-supervised video object segmentation on resource-constrained devices, such as mobile phones. We formulate this problem as a distillation task, whereby we demonstrate that small space-time-memory…
In this paper, we tackle a new problem: how to transfer knowledge from the pre-trained cumbersome yet well-performed CNN-based model to learn a compact Vision Transformer (ViT)-based model while maintaining its learning capacity? Due to the…
Spiking Neural Networks (SNNs) exhibit exceptional energy efficiency on neuromorphic hardware due to their sparse activation patterns. However, conventional training methods based on surrogate gradients and Backpropagation Through Time…
4D radar super-resolution, which aims to reconstruct sparse and noisy point clouds into dense and geometrically consistent representations, is a foundational problem in autonomous perception. However, existing methods often suffer from high…
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…
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…
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…