- ResNeXt{50,101,152}
- ResNet{50,101,152}
- Xception
- GoogLeNet v4
- VGG{16,19}
- GoogLeNet v3
- GoogLeNet v2
- GoogLeNet v1
- Feature Pyramid Networks (with ResNet/ResNeXt)
- Mask R-CNN. Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. IEEE International Conference on Computer Vision (ICCV), 2017. -- Marr Prize at ICCV 2017
- YOLO v3.
- RetinaNet. Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. IEEE International Conference on Computer Vision (ICCV), 2017. -- Best Student Paper Award at ICCV 2017
- Faster R-CNN Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Conference on Neural Information Processing Systems (NIPS), 2015.
- Fast R-CNN. Ross Girshick. IEEE International Conference on Computer Vision (ICCV), 2015.
- YOLO v2.
- YOLO v1.
- RPN
- R-FCN. Jifeng Dai, Yi Li, Kaiming He, and Jian Sun. Conference on Neural Information Processing Systems (NIPS), 2016.
- 1.各种卷积总结，CNN中千奇百怪的卷积方式大汇总
- 2.FaceBook 的 Detectron实现，使用Detectron进行目标检测
- 3.YOLOv3小的实现，YOLOv3: 训练自己的数据
- 4.GoogLeNet Inception，GoogLeNet 之 Inception(V1-V4)
- 5.FAIR最新视觉论文集锦：FPN，RetinaNet，Mask 和 Mask-X RCNN
- 6.图解YOLO：图解YOLO
- 7.关于目标检测模型评估指标，目标检测模型的评估指标mAP
- 8.YOLO幻灯片，ppt