版权声明:转载请注明出处 https://cloud.tencent.com/developer/article/1347418
Year | Month | Algorithm | Improve | Conference |
---|---|---|---|---|
2012 | | AlexNet | basemodel (R-CNN、SPPNet) | ImageNet2012 1st、NIPS2012 |
= | = | = | = | = |
2013 | 11 | R-CNN | traditional method -> CNN method、proposal、target method | CVPR2014 |
2013 | 11 | ZFNet | basemodel (Faster R-CNN) | |
= | = | = | = | = |
2014 | 6 | SPPNet | share feature extraction、SPP layer | ECCV2014 |
2014 | 9 | GoogleNet | basemodel (YOLOv1) | ImageNet2014 2nd |
2014 | 9 | VGGNet | basemodel (Fast R-CNN、Faster R-CNN、SSD) | ImageNet2014 1st |
= | = | = | = | = |
2015 | 2 | BN | easy to adjust parameters & accelerate convergence | |
2015 | 4 | Fast R-CNN | 4-stage -> 2-stage、RoIPooling、Softmax、Smooth L1、mini-batch=2 | ICCV2015 |
2015 | 6 | Faster R-CNN | SS -> RPN、anchor method、new target method | NIPS2015 |
2015 | 6 | YOLOv1 | 1-stage、real-time | CVPR2016 |
2015 | 12 | SSD | feature pyramid、precise 1-stage、multi-anchor method、FCN backbone | ECCV2016 |
2015 | 12 | ResNet | basemodel (R-FCN、FPN、Mask R-CNN、RetinaNet)、identity mapping | ImageNet2015 1st、CVPR2016 Best Paper |
= | = | = | = | = |
2016 | 5 | R-FCN | share roi-wise subnet、2-stage FCN backbone | NIPS2016 |
2016 | 8 | DenseNet | precise-basemodel | |
2016 | 10 | Xception | light-basemodel | |
2016 | 11 | ResNeXt | precise-basemodel | |
2016 | 11 | Speed/accuracy trade-offs | analyse detection | |
2016 | 12 | YOLOv2 | large-scale detector、multi-scale training、joint training | CVPR2017 Best Paper Mention |
2016 | 12 | FPN | enhanced-feature pyramid | CVPR2017 |
= | = | = | = | = |
2017 | 1 | DSSD | SSD+FPN | |
2017 | 3 | Mask R-CNN | RoIPooling -> RoIAlign | ICCV2017 Best Paper |
2017 | 3 | DCN | deformable module | |
2017 | 4 | Soft-NMS | eclectic version of NMS | |
2017 | 4 | MobileNet | light-basemodel | |
2017 | 7 | ShuffleNet | light-basemodel | |
2017 | 7 | DPN | basemodel | ImageNet2017 1st |
2017 | 8 | RetinaNet | CE -> FL、best 1-stage | ICCV2017 Best Student Paper |
2017 | 11 | MegDet | large mini-batch | COCO2017 1st、CVPR2018 |
2017 | 11 | Light-head R-CNN | light-head | |
2017 | 11 | Relation Network | | |
2017 | 11 | SNIP | image pyramid | CVPR2018 |
2017 | 12 | Cascade R-CNN | cascade method、2-stage -> 4-stage | CVPR2018 |
2017 | 12 | R-FCN-3000 | precise large-scale detector | |
= | = | = | = | = |
2018 | 3 | PAN | FPN -> PAN | COCO2017 2nd |
2018 | 4 | YOLOv3 | | |
2018 | 4 | DetNet | detection-backbone | |
2018 | 5 | SNIPER | | |
2018 | 6 | Understanding BN | analyse BN | |