Related papers: FFCV: Accelerating Training by Removing Data Bottl…

Compression of a neural network can help in speeding up both the training and the inference of the network. In this research, we study applying compression using low rank decomposition on network layers. Our research demonstrates that to…

We introduce Multi-Lane Capsule Networks (MLCN), which are a separable and resource efficient organization of Capsule Networks (CapsNet) that allows parallel processing, while achieving high accuracy at reduced cost. A MLCN is composed of a…

Data-Free Meta-Learning (DFML) aims to extract knowledge from a collection of pre-trained models without requiring the original data, presenting practical benefits in contexts constrained by data privacy concerns. Current DFML methods…

Computer Vision (CV) is playing a significant role in transforming society by utilizing machine learning (ML) tools for a wide range of tasks. However, the need for large-scale datasets to train ML models creates challenges for centralized…

Support Vector Machines (SVM), a popular machine learning technique, has been applied to a wide range of domains such as science, finance, and social networks for supervised learning. Whether it is identifying high-risk patients by…

Federated Learning (FL) is a collaborative method for training models while preserving data privacy in decentralized settings. However, FL encounters challenges related to data heterogeneity, which can result in performance degradation. In…

Vision-Language-Navigation (VLN) models exhibit excellent navigation accuracy but incur high computational overhead. Token caching has emerged as a promising training-free strategy to reduce this cost by reusing token computation results;…

Training deep neural networks often requires careful hyper-parameter tuning and significant computational resources. In this paper, we propose ConvTimeNet (CTN): an off-the-shelf deep convolutional neural network (CNN) trained on diverse…

Neural representations for video (NeRV) have gained considerable attention for their strong performance across various video tasks. However, existing NeRV methods often struggle to capture fine spatial details, resulting in vague…

This paper presents FLGC, a simple yet effective fully linear graph convolutional network for semi-supervised and unsupervised learning. Instead of using gradient descent, we train FLGC based on computing a global optimal closed-form…

While large neural networks demonstrate higher performance in various tasks, training large networks is difficult due to limitations on GPU memory size. We propose a novel out-of-core algorithm that enables faster training of extremely…

Dense pixel-wise image prediction has been advanced by harnessing the capabilities of Fully Convolutional Networks (FCNs). One central issue of FCNs is the limited capacity to handle joint upsampling. To address the problem, we present a…

Most video restoration networks are slow, have high computational load, and can't be used for real-time video enhancement. In this work, we design an efficient and fast framework to perform real-time video enhancement for practical…

The channel redundancy in feature maps of convolutional neural networks (CNNs) results in the large consumption of memories and computational resources. In this work, we design a novel Slim Convolution (SlimConv) module to boost the…

Learning algorithms for Deep Neural Networks are typically based on supervised end-to-end Stochastic Gradient Descent (SGD) training with error backpropagation (backprop). Backprop algorithms require a large number of labelled training…

The Versatile Video Coding (VVC) standard has been finalized by Joint Video Exploration Team (JVET) in 2020. Compared to the High Efficiency Video Coding (HEVC) standard, VVC offers about 50% compression efficiency gain, in terms of…

Recently, learned video compression has drawn lots of attention and show a rapid development trend with promising results. However, the previous works still suffer from some criticial issues and have a performance gap with traditional…

Large language models (LLMs) are widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant deployment challenges, primarily due to the KV cache whose size…

Convolutional neural network (CNN) has achieved impressive success in computer vision during the past few decades. The image convolution operation helps CNNs to get good performance on image-related tasks. However, the image convolution has…

Autoregressive convolutional neural networks (CNNs) have been widely exploited for sequence generation tasks such as audio synthesis, language modeling and neural machine translation. WaveNet is a deep autoregressive CNN composed of several…