Related papers: Image Captioning with Sparse Recurrent Neural Netw…
Pruning neural networks has proven to be a successful approach to increase the efficiency and reduce the memory storage of deep learning models without compromising performance. Previous literature has shown that it is possible to achieve a…
Image captioning models are becoming increasingly successful at describing the content of images in restricted domains. However, if these models are to function in the wild - for example, as assistants for people with impaired vision - a…
Filter level pruning is an effective method to accelerate the inference speed of deep CNN models. Although numerous pruning algorithms have been proposed, there are still two open issues. The first problem is how to prune residual…
In automatic speech recognition (ASR), model pruning is a widely adopted technique that reduces model size and latency to deploy neural network models on edge devices with resource constraints. However, multiple models with different…
Channel pruning is widely accepted to accelerate modern convolutional neural networks (CNNs). The resulting pruned model benefits from its immediate deployment on general-purpose software and hardware resources. However, its large pruning…
Convolutional Sparse Coding (CSC) has been attracting more and more attention in recent years, for making full use of image global correlation to improve performance on various computer vision applications. However, very few studies focus…
Recurrent neural networks (RNNs) achieve cutting-edge performance on a variety of problems. However, due to their high computational and memory demands, deploying RNNs on resource constrained mobile devices is a challenging task. To…
Pruning of deep neural networks has been an effective technique for reducing model size while preserving most of the performance of dense networks, crucial for deploying models on memory and power-constrained devices. While recent sparse…
Deep Convolutional Neural Networks (CNNs) are widely employed in modern computer vision algorithms, where the input image is convolved iteratively by many kernels to extract the knowledge behind it. However, with the depth of convolutional…
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…
Typical techniques for video captioning follow the encoder-decoder framework, which can only focus on one source video being processed. A potential disadvantage of such design is that it cannot capture the multiple visual context…
The pruning objective has recently extended beyond accuracy and sparsity to robustness in language models. Despite this, existing methods struggle to enhance robustness against adversarial attacks when continually increasing model sparsity…
Image captioning often requires a large set of training image-sentence pairs. In practice, however, acquiring sufficient training pairs is always expensive, making the recent captioning models limited in their ability to describe objects…
Even though rate-distortion optimization is a crucial part of traditional image and video compression, not many approaches exist which transfer this concept to end-to-end-trained image compression. Most frameworks contain static compression…
Due to the significant computational challenge of training large-scale graph neural networks (GNNs), various sparse learning techniques have been exploited to reduce memory and storage costs. Examples include \textit{graph sparsification}…
Restoring high-quality CT images from low dose CT counterparts is an ill-posed, nonlinear problem to which Deep Learning approaches have been giving superior solutions compared to classical model-based approaches. In this article, a…
Linear recurrent neural networks enable powerful long-range sequence modeling with constant memory usage and time-per-token during inference. These architectures hold promise for streaming applications at the edge, but deployment in…
Recurrent neural networks (RNNs) have achieved state-of-the-art performances in many natural language processing tasks, such as language modeling and machine translation. However, when the vocabulary is large, the RNN model will become very…
Real time application of deep learning algorithms is often hindered by high computational complexity and frequent memory accesses. Network pruning is a promising technique to solve this problem. However, pruning usually results in irregular…
Spiking Neural Networks (SNNs) have gained significant attention due to the energy-efficient and multiplication-free characteristics. Despite these advantages, deploying large-scale SNNs on edge hardware is challenging due to limited…