Related papers: C3-SL: Circular Convolution-Based Batch-Wise Compr…
This paper proposes a novel communication-efficient split learning (SL) framework, named SplitFC, which reduces the communication overhead required for transmitting intermediate feature and gradient vectors during the SL training process.…
One of the practical choices for making a lightweight semantic segmentation model is to combine a depth-wise separable convolution with a dilated convolution. However, the simple combination of these two methods results in an…
The expanding scale of neural networks poses a major challenge for distributed machine learning, particularly under limited communication resources. While split learning (SL) alleviates client computational burden by distributing model…
For distributed learning among collaborative users, this paper develops and analyzes a communication-efficient scheme for federated learning (FL) over the air, which incorporates 1-bit compressive sensing (CS) into analog aggregation…
Model compression and acceleration are attracting increasing attentions due to the demand for embedded devices and mobile applications. Research on efficient convolutional neural networks (CNNs) aims at removing feature redundancy by…
Multi-scale techniques have achieved great success in a wide range of computer vision tasks. However, while this technique is incorporated in existing works, there still lacks a comprehensive investigation on variants of multi-scale…
Deep convolutional neural networks achieve remarkable visual recognition performance, at the cost of high computational complexity. In this paper, we have a new design of efficient convolutional layers based on three schemes. The 3D…
Deep learning generally suffers from enormous computational resources and time-consuming training processes. Broad Learning System (BLS) and its convolutional variants have been proposed to mitigate these issues and have achieved superb…
This paper proposes a novel deep subspace clustering approach which uses convolutional autoencoders to transform input images into new representations lying on a union of linear subspaces. The first contribution of our work is to insert…
We present Smol-GS, a novel method for learning compact representations for 3D Gaussian Splatting (3DGS). Our approach learns highly efficient splat-wise features to model 3D space which capture abstracted cues, including color, opacity,…
Although equirectangular projection (ERP) is a convenient form to store omnidirectional images (also known as 360-degree images), it is neither equal-area nor conformal, thus not friendly to subsequent visual communication. In the context…
Deep Convolutional Neural Networks (CNN) have been successfully applied to many real-life problems. However, the huge memory cost of deep CNN models poses a great challenge of deploying them on memory-constrained devices (e.g., mobile…
Over the past few years, dictionary learning (DL)-based methods have been successfully used in various image reconstruction problems. However, traditional DL-based computed tomography (CT) reconstruction methods are patch-based and ignore…
This paper introduces a novel framework designed to achieve a high compression ratio in Split Learning (SL) scenarios where resource-constrained devices are involved in large-scale model training. Our investigations demonstrate that…
This paper proposes a novel communication-efficient Split Learning (SL) framework, named Attention-based Double Compression (ADC), which reduces the communication overhead required for transmitting intermediate Vision Transformers…
The increasing complexity of neural networks poses a significant barrier to the deployment of distributed machine learning (ML) on resource-constrained devices, such as federated learning (FL). Split learning (SL) offers a promising…
We introduce the concept of compressed convolution, a technique to convolve a given data set with a large number of non-orthogonal kernels. In typical applications our technique drastically reduces the effective number of computations. The…
State-of-the-art 2D image compression schemes rely on the power of convolutional neural networks (CNNs). Although CNNs offer promising perspectives for 2D image compression, extending such models to omnidirectional images is not…
Learned image compression (LIC) has recently made significant progress, surpassing traditional methods. However, most LIC approaches operate mainly in the spatial domain and lack mechanisms for reducing frequency-domain correlations. To…
Contrastive learning (CL) aims to learn useful representation without relying on expert annotations in the context of medical image segmentation. Existing approaches mainly contrast a single positive vector (i.e., an augmentation of the…