Related papers: A Variational Information Bottleneck Based Method …
Besides accuracy, the model size of convolutional neural networks (CNN) models is another important factor considering limited hardware resources in practical applications. For example, employing deep neural networks on mobile systems…
Recurrent Neural Network (RNN) and its variations such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), have become standard building blocks for learning online data of sequential nature in many research areas, including…
The problem of a deep learning model losing performance on a previously learned task when fine-tuned to a new one is a phenomenon known as Catastrophic forgetting. There are two major ways to mitigate this problem: either preserving…
Recent advances in vision-language models (VLMs) have shown remarkable performance across multimodal tasks, yet their ever-growing scale poses severe challenges for deployment and efficiency. Existing compression methods often rely on…
Model compression is an essential technique for deploying deep neural networks (DNNs) on power and memory-constrained resources. However, existing model-compression methods often rely on human expertise and focus on parameters' local…
This paper investigates task-oriented communication for edge inference, where a low-end edge device transmits the extracted feature vector of a local data sample to a powerful edge server for processing. It is critical to encode the data…
Deep neural networks have achieved strong performance in image classification tasks due to their ability to learn complex patterns from high-dimensional data. However, their large computational and memory requirements often limit deployment…
Integration of information from non-auditory cues can significantly improve the performance of speech-separation models. Often such models use deep modality-specific networks to obtain unimodal features, and risk being too costly or…
Compressing neural network architectures is important to allow the deployment of models to embedded or mobile devices, and pruning and quantization are the major approaches to compress neural networks nowadays. Both methods benefit when…
Neural networks have been notorious for being computationally expensive. This is mainly because neural networks are often over-parametrized and most likely have redundant nodes or layers as they are getting deeper and wider. Their demand…
While Convolutional Neural Networks (CNNs) excel at learning complex latent-space representations, their over-parameterization can lead to overfitting and reduced performance, particularly with limited data. This, alongside their high…
Existing high-performance deep learning models require very intensive computing. For this reason, it is difficult to embed a deep learning model into a system with limited resources. In this paper, we propose the novel idea of the network…
Deep spiking neural networks (SNNs) have emerged as a potential alternative to traditional deep learning frameworks, due to their promise to provide increased compute efficiency on event-driven neuromorphic hardware. However, to perform…
Neural network pruning is an important step in design process of efficient neural networks for edge devices with limited computational power. Pruning is a form of knowledge transfer from the weights of the original network to a smaller…
Deep Neural Nets (DNNs) learn latent representations induced by their downstream task, objective function, and other parameters. The quality of the learned representations impacts the DNN's generalization ability and the coherence of the…
As in many other different fields, deep learning has become the main approach in most computer vision applications, such as scene understanding, object recognition, computer-human interaction or human action recognition (HAR). Research…
We propose a novel deep supervised neural network for the task of action recognition in videos, which implicitly takes advantage of visual tracking and shares the robustness of both deep Convolutional Neural Network (CNN) and Recurrent…
Motivated by the ever-increasing demands for limited communication bandwidth and low-power consumption, we propose a new methodology, named joint Variational Autoencoders with Bernoulli mixture models (VAB), for performing clustering in the…
Learned representations at the level of characters, sub-words, words and sentences, have each contributed to advances in understanding different NLP tasks and linguistic phenomena. However, learning textual embeddings is costly as they are…
Most existing Convolutional Neural Networks(CNNs) used for action recognition are either difficult to optimize or underuse crucial temporal information. Inspired by the fact that the recurrent model consistently makes breakthroughs in the…