Object Detection 模型整理 (持续更新)

依然主要关注网络结构。

网络

• SPPNet: Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition, ECCV, 2014
• R-CNN: Rich feature hierarchies for accurate object detection and semantic segmentation, CVPR, 2014
• Fast R-CNN, ICCV, 2015
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, NIPS, 2015
• FPN: Feature Pyramid Networks for Object Detection, CVPR, 2017
• SSD: Single Shot MultiBox Detector, ECCV, 2016
• DSSD: Deconvolutional Single Shot Detector, CVPR, 2017
• FSSD: Feature Fusion Single Shot Multibox Detector, arXiv, 2017
• YOLO-v1: You Only Look Once: Unified, Real-Time Object Detection, ECCV, 2016
• YOLO-v2: YOLO9000: Better, Faster, Stronger, arXiv, 2016
• YOLO-v3: YOLOv3: An Incremental Improvement
• R-FCN: Object Detection via Region-based Fully Convolutional Networks, NIPS, 2016
• Deformable Convolutional Networks, ICCV, 2017
• Faster R-CNN+SSD: Single-Shot Refinement Neural Network for Object Detection, CVPR, 2018
• CornerNet: Detecting Objects as Paired Keypoints, ECCV, 2018
• IoUNet: Acquisition of Localization Confidence for Accurate Object Detection, ECCV, 2018

理论

• RetinaNet: Focal Loss for Dense Object Detection, ICCV, 2017