Science Daily

Light-powered chip makes AI 100 times more efficient

Artificial intelligence is consuming enormous amounts of energy, but researchers at the University of Florida have built a chip that could change everything by using light instead of electricity for a ...
IEEE

Transformable Dilated Convolution by Distance for LiDAR Semantic Segmentation

Abstract: LiDAR semantic segmentation is essential in autonomous vehicle safety. A rotating 3D LiDAR projects more laser points onto nearby objects and fewer points onto farther objects. Therefore, ...
IEEE

Deep Convolution Modulation for Image Super-Resolution

Abstract: Recently, deep-learning-based super-resolution methods have achieved excellent performances, but mainly focus on training a single generalized deep network by feeding numerous samples. Yet ...
IEEE

FDLNet: Boosting Real-time Semantic Segmentation by Image-size Convolution via Frequency Domain Learning

Abstract: This paper proposes a novel real-time semantic segmentation network via frequency domain learning, called FDLNet, which revisits the segmentation task from two critical perspectives: spatial ...
IEEE

DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention

Abstract: Single image dehazing is a challenging ill-posed problem which estimates latent haze-free images from observed hazy images. Some existing deep learning based methods are devoted to improving ...
IEEE

Rotational Convolution: Rethinking Convolution for Downside Fisheye Images

Abstract: It has long been recognized that the standard convolution is not rotation equivariant and thus not appropriate for downside fisheye images which are rotationally symmetric. This paper ...
IEEE

CDC-YOLOFusion: Leveraging Cross-Scale Dynamic Convolution Fusion for Visible-Infrared Object Detection

Abstract: Feature-level fusion methods have demonstrated superior performance for visible-infrared object detection due to the deep exploration of visible and infrared features. However, most existing ...
IEEE

From Cluster Assumption to Graph Convolution: Graph-Based Semi-Supervised Learning Revisited

Abstract: Graph-based semi-supervised learning (GSSL) has long been a research focus. Traditional methods are generally shallow learners, based on the cluster assumption. Recently, graph convolutional ...
IEEE

Constructing New Backbone Networks via Space-Frequency Interactive Convolution for Deepfake Detection

Abstract: The serious concerns over the negative impacts of Deepfakes have attracted wide attentions in the community of multimedia forensics. The existing detection works achieve deepfake detection ...
IEEE

PTC-Net: Point-Wise Transformer With Sparse Convolution Network for Place Recognition

Abstract: In the point-cloud-based place recognition area, the existing hybrid architectures combining both convolutional networks and transformers have shown promising performance. They mainly apply ...
IEEE

Bridge Graph Attention Based Graph Convolution Network With Multi-Scale Transformer for EEG Emotion Recognition

Abstract: In multichannel electroencephalograph (EEG) emotion recognition, most graph-based studies employ shallow graph model for spatial characteristics learning due to node over-smoothing caused by ...
IEEE

On-Chip Photonic Convolution Framework Enabled by Fine-Grained Diffractive Slabs With Reduced Error and Wavelength Insensitivity

Abstract: Silicon nitride photonic integrated platforms, characterized by ultra-low propagation loss, broad transparency window, high power-handling capacity, and full CMOS compatibility, present a ...