Morning Overview on MSN

Photonic AI chip targets faster convolutions with far less energy

Engineers at the University of Florida have built a photonic chip that performs convolutions, the most compute-heavy operation in modern AI, using light instead of electricity and delivering roughly ...
IEEE

Adaptive Guided Convolution Generated With Spatial Relationships for Point Clouds Analysis

Abstract: Representing valuable semantics in irregular 3-D point clouds with spatial-variant relationships is challenging. Current shared/weighted point convolution methods have limited efficiency and ...
IEEE

Optimizing the Convolution Operation to Accelerate Deep Neural Networks on FPGA

Abstract: As convolution contributes most operations in convolutional neural network (CNN), the convolution acceleration scheme significantly affects the efficiency and performance of a hardware CNN ...
GitHub

Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

pip install -r requirements.txt pip install -e . If you use any part of this code and pretrained weights for your own purpose, please cite our paper. @InProceedings ...
GitHub

Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening

Abstract: Currently, machine learning-based methods for remote sensing pansharpening have progressed rapidly. However, existing pansharpening methods often do not fully exploit differentiating ...