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

Abstract

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. The proposed networks respect the variability of the gradients by integrating feature maps from the beginning and the end of a network stage, which, in our experiments, reduces computations by 20% with equivalent or even superior accuracy on the ImageNet dataset, and significantly outperforms state-of-the-art approaches in terms of AP50 on the MS COCO object detection dataset. The CSPNet is easy to implement and general enough to cope with architectures based on ResNet, ResNeXt, and DenseNet. Source code is at https://github.com/WongKinYiu/CrossStagePartialNetworks.

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• YOLOv3: An Incremental Improvement
• Res2Net: A New Multi-scale Backbone Architecture
• ParseNet: Looking Wider to See Better
• Searching for Activation Functions
• FreeAnchor: Learning to Match Anchors for Visual Object Detection
• Light-Head R-CNN: In Defense of Two-Stage Object Detector
• CornerNet-Lite: Efficient Keypoint Based Object Detection
• ThunderNet: Towards Real-time Generic Object Detection
• Training-Time-Friendly Network for Real-Time Object Detection

Cited by in corpus (8)

• Aerial Images Processing for Car Detection using Convolutional Neural Networks: Comparison between Faster R-CNN and YoloV3
• EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approach
• Continuous Human Action Recognition for Human-Machine Interaction: A Review
• Facial Expression Recognition and Image Description Generation in Vietnamese
• Edge-Cloud Collaborated Object Detection via Difficult-Case Discriminator
• Developing a Compressed Object Detection Model based on YOLOv4 for Deployment on Embedded GPU Platform of Autonomous System
• Non-invasive hemodynamic analysis for aortic regurgitation using computational fluid dynamics and deep learning
• Multiple Myeloma Cancer Cell Instance Segmentation