Related papers: ISCS: Parameter-Guided Feature Pruning for Resourc…

Convolutional Neural Networks (CNNs) pre-trained on large-scale datasets such as ImageNet are widely used as feature extractors to construct high-accuracy classification models from scarce data for specific tasks. In such scenarios,…

Federated Learning (FL) is a privacy-preserving distributed deep learning paradigm that involves substantial communication and computation effort, which is a problem for resource-constrained mobile and IoT devices. Model…

The traditional SegNet architecture commonly encounters significant information loss during the sampling process, which detrimentally affects its accuracy in image semantic segmentation tasks. To counter this challenge, we introduce an…

Neural network pruning is a fruitful area of research with surging interest in high sparsity regimes. Benchmarking in this domain heavily relies on faithful representation of the sparsity of subnetworks, which has been traditionally…

We propose to employ a saliency-driven hierarchical neural image compression network for a machine-to-machine communication scenario following the compress-then-analyze paradigm. By that, different areas of the image are coded at different…

Implicit Neural Point Cloud (INPC) is a recent hybrid representation that combines the expressiveness of neural fields with the efficiency of point-based rendering, achieving state-of-the-art image quality in novel view synthesis. However,…

Recently there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations.The key idea is to rank the filters based on a certain criterion (say, l1-norm) and retain…

Modern applications require lightweight neural network models. Most existing neural network pruning methods focus on removing unimportant filters; however, these may result in the loss of statistical information after pruning due to failing…

Scene Graph Generation (SGG) suffers from a long-tailed distribution, where a few predicate classes dominate while many others are underrepresented, leading to biased models that underperform on rare relations. Unbiased-SGG methods address…

Integrated sensing and communication (ISAC) and intelligent reflecting surface (IRS) are viewed as promising technologies for future generations of wireless networks. This paper investigates the channel estimation problem in an IRS-assisted…

The human visual system employs a selective attention mechanism to understand the visual world in an eficient manner. In this paper, we show how computational models of this mechanism can be exploited for the computer vision application of…

In this work, we propose an efficient and effective approach for unconstrained salient object detection in images using deep convolutional neural networks. Instead of generating thousands of candidate bounding boxes and refining them, our…

Joint source-channel coding (JSCC) is an effective approach for semantic communication. However, current JSCC methods are difficult to integrate with existing communication network architectures, where application and network providers are…

The realization of practical intelligent reflecting surface (IRS)-assisted multi-user communication (IRS-MUC) systems critically depends on the proper beamforming design exploiting accurate channel state information (CSI). However, channel…

Employing large intelligent surfaces (LISs) is a promising solution for improving the coverage and rate of future wireless systems. These surfaces comprise a massive number of nearly-passive elements that interact with the incident signals,…

This paper investigates the integrated sensing and communication (ISAC) in vehicle-to-infrastructure (V2I) networks. To realize ISAC, an effective beamforming design is essential which however, highly depends on the availability of accurate…

Deeper and wider Convolutional Neural Networks (CNNs) achieve superior performance but bring expensive computation cost. Accelerating such over-parameterized neural network has received increased attention. A typical pruning algorithm is a…

Inference for Deep Neural Networks is increasingly being executed locally on mobile and embedded platforms due to its advantages in latency, privacy and connectivity. Since modern System on Chips typically execute a combination of different…

The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years. Indeed, those methods allowed to find lighter and faster networks, able to perform more efficiently in resource-constrained…

Self-supervised speech representation learning (SSL) has shown to be effective in various downstream tasks, but SSL models are usually large and slow. Model compression techniques such as pruning aim to reduce the model size and computation…