CSPNet: A New Backbone that can Enhance Learning Capability of CNN

Understand

Neural networks have enabled state-of-the-art approaches to achieve incredible results on computer vision tasks such as object detection.

• However, such success greatly relies on costly computation resources, which hinders people with cheap devices from appreciating the advanced technology.
• In this paper, we propose Cross Stage Partial Network (CSPNet) to mitigate the problem that previous works require heavy inference computations from the network architecture perspective.
• We attribute the problem to the duplicate gradient information within network optimization.