Channel Attention Networks

In this work, we propose Channel Attention Networks (CAN), a deep learning model that uses soft attention on individual channels. We jointly train this model end-to-end on SpaceNet, a challenging multi-spectral semantic segmentation dataset.

Authors

Alexei Bastidas

Deep Learning Data Scientist, Intel AI Lab

View authors bio

Hanlin Tang

Senior Director of the AI Lab, Artificial Intelligence Platforms Group

View authors bio

Related Content

Using A Priori Knowledge to Improve Scene Understanding

Existing semantic segmentation algorithms treat images in isolation, but autonomous vehicles often revisit the same locations. We propose leveraging this...

View publication

Intel® Nervana™ NNP-I Shows Best-in-Class Throughput on BERT...

Natural Language Processing (NLP) will be a 43 billion dollar business by 2025. Cutting-edge models like Google’s BERT (Bidirectional Encoder...

View publication

Enhanced low-precision pipeline to accelerate inference with OpenVINO...

Overview Neural network quantization and execution in low precision have been widely adopted as an optimization method that can achieve...

View publication

Improving Stroke Care and More With AI-Aided Medical...

Capital Health is using MaxQ AI’s ACCIPIO medical diagnostics solution, running on AI technologies from Intel, to help patients with...

View publication

Stay Connected


Keep tabs on all the latest news with our monthly newsletter.