特别感谢实验室小雷同学汇总此篇,日后学习目标跟踪可以有个好的方向好的借鉴,哪怕是比赛的时候选模型都可以参考一下。
----------------------------------------------------------
论文对应序号 | method | dataset | code | ||
|
| VOC2007 | VOC2012 | COCO |
|
1 | Cascade R-CNN |
|
| 42.8(AP) | 有 |
2 | Relation Net |
|
| 39.0(加到别的方法上) | 有 |
3 | RefineDet | 85.8 | 86.8 | 41.8(AP) | 有 |
4 | SNIP |
|
|
| 有 |
5 | R-FCN-3000 | 43.3(ImageNet) | 无 | ||
6 | DES | 84.3 | 83.7 | 32.8 | 无 |
7 | STDN | 80.9 |
| 31.8 | 有 |
8 | W2F | 52.4 | 47.8 |
| 无 |
9 | 无简写 | 51.2 |
|
| 无 |
10 | MELM | 47.3 | 42.4 |
| 有 |
11 | SSM | 62.9 |
|
| 有 |
12 | 无简写 | 82.9 |
| 35.6(AP) | 有 |
13 | PAD | 80.7 | 79.5 |
| 无 |
14 | ZLDN | 47.6 | 42.9 |
| 无 |
15 | 无简写 |
|
| 39.5 | 无 |
16 | MegDet |
|
| 52.5(mmAP) | 无 |
17 | drl-RPN | 76.4 | 72.2 |
| 有 |
18 | SIN | 76.0 | 73.1 | 23.2(AP) | 有 |
19 | SOD-MTGAN |
|
| 41.4(AP) | 无 |
20 | ML-LocNet | 49.7 | 43.6 | 16.2(COCO2014) | 无 |
21 | DetNet |
|
| 40.3 | 有 |
22 | 无简写 | 50.4 | 69.3 |
| 无 |
23 | 无简写 | 25.4 | 22.9 |
| 无 |
24 | 无简写 | 82.4 | 81.1 | 34.6(AP) | 无 |
25 | RFB-NET | 82.2 |
| 29.7(COCO2014) 34.4(COCO2015) | 有 |
26 | PFP-NET | 84.1 | 83.7 | 41.8 | 有 |
27 | TS2C | 44.3 | 40.0 |
| 无 |
28 | SAN | 82.8 |
| 43.4 | 无 |
29 | 无简写 |
| 81.2 | mmAP:39.3(COCO2017) | 无 |
30 | 无简写 |
|
| 42.0(AP) | 无 |
附:
(1)论文对应序号中,序号1-18篇收录于CVPR,19-30收录于ECCV。
(2)在经典数据库的检测精度取在论文中实现的最高精度,不考虑base network。
(3)method列仅写出算法简称。
(4)针对COCO数据集的检测结果不可进行统一比较。有的是在COCO2014、COCO2015或者是COCO2017上测试,评价指标稍有不同。
(5)CVPR2019论文未公布。
======以下排名仅对论文中有在对应数据集测试的算法进行排序=========
VOC2007数据集排名
论文对应序号 | method | mAP | 排名 |
3 | RefineDet | 85.8 | 1 |
6 | DES | 84.3 | 2 |
26 | PFP-NET | 84.1 | 3 |
12 | 无简写 | 82.9 | 4 |
28 | SAN | 82.8 | 5 |
24 | 无简写 | 82.4 | 6 |
25 | RFB-NET | 82.2 | 7 |
7 | STDN | 80.9 | 8 |
13 | PAD | 80.7 | 9 |
17 | drl-RPN | 76.4 | 10 |
18 | SIN | 76.0 | 11 |
11 | SSM | 62.9 | 12 |
8 | W2F | 52.4 | 13 |
9 | 无简写 | 51.2 | 14 |
22 | 无简写 | 50.4 | 15 |
20 | ML-LocNet | 49.7 | 16 |
14 | ZLDN | 47.6 | 17 |
10 | MELM | 47.3 | 18 |
27 | TS2C | 44.3 | 19 |
23 | 无简写 | 25.4 | 20 |
VOC2012数据集排名
论文对应序号 | method | mAP | 排名 |
3 | RefineDet | 86.8 | 1 |
6 | DES | 83.7 | 2 |
26 | PFP-NET | 83.7 | 2 |
29 | 无简写 | 81.2 | 3 |
24 | 无简写 | 81.1 | 4 |
13 | PAD | 79.5 | 5 |
18 | SIN | 73.1 | 6 |
17 | drl-RPN | 72.2 | 7 |
22 | 无简写 | 69.3 | 8 |
8 | W2F | 47.8 | 9 |
20 | ML-LocNet | 43.6 | 10 |
14 | ZLDN | 42.9 | 11 |
10 | MELM | 42.4 | 12 |
27 | TS2C | 40.0 | 13 |
23 | 无简写 | 22.9 | 14 |
22 | 无简写 | 50.4 | 15 |
20 | ML-LocNet | 49.7 | 16 |
14 | ZLDN | 47.6 | 17 |
10 | MELM | 47.3 | 18 |
27 | TS2C | 44.3 | 19 |
23 | 无简写 | 25.4 | 20 |
COCO数据集排名
论文对应序号 | method | mAP | 排名 |
16 | MegDet | 52.5(mmAP) | 1 |
28 | SAN | 43.4 | 2 |
1 | Cascade R-CNN | 42.8(AP) | 3 |
30 | 无简写 | 42.0(AP) | 4 |
26 | PFP-NET | 41.8 | 5 |
3 | RefineDet | 41.8(AP) | 6 |
19 | SOD-MTGAN | 41.4(AP) | 7 |
21 | DetNet | 40.3 | 8 |
15 | 无简写 | 39.5 | 9 |
29 | 无简写 | mmAP:39.3(COCO2017) | 10 |
2 | Relation Net | 39.0(加到别的方法上) | 11 |
12 | 无简写 | 35.6(AP) | 12 |
24 | 无简写 | 34.6(AP) | 13 |
25 | RFB-NET | 29.7(COCO2014) 34.4(COCO2015) | 14 |
6 | DES | 32.8 | 15 |
7 | STDN | 31.8 | 16 |
18 | SIN | 23.2(AP) | 17 |
20 | ML-LocNet | 16.2(COCO2014) | 18 |
1、Cascaded RCNN
论文 | Cascade R-CNN : Delving into High Quality Object Detection |
论文链接 | https://arxiv.org/abs/1712.00726 |
代码链接 | https://github.com/zhaoweicai/cascade-rcnn |
实验结果
2、Relation Net
论文 | Relation Networks for Object Detection |
论文链接 | https://arxiv.org/abs/1711.11575 |
代码链接 | https://github.com/msracver/Relation-Networks-for-Object-Detection |
实验结果
(实验是针对two stage系列的目标检测算法而言,在ROI Pooling后的两个全连接层和NMS模块引入object relation module,如Figure1所示,因此做到了完整的end-to-end训练。)
3、RefineDet
论文 | Single-Shot Refinement Neural Network for Object Detection |
论文链接 | https://arxiv.org/abs/1711.06897 |
代码链接 | https://github.com/sfzhang15/RefineDet |
实验结果
4、SNIP
论文 | An Analysis of Scale Invariance in Object Detection – SNIP |
论文链接 | https://arxiv.org/abs/1711.08189 |
代码链接 | http://bit.ly/2yXVg4c(打不开) |
实验结果
5、R-FCN-3000
论文 | R-FCN-3000 at 30fps: Decoupling Detection and Classification |
论文链接 | https://arxiv.org/abs/1712.01802 |
代码链接 |
|
ImageNet实验结果
6、DES
论文 | Single-Shot Object Detection with Enriched Semantics |
论文链接 | https://arxiv.org/abs/1712.00433 |
代码链接 |
|
实验结果
7、STDN
论文 | Scale-Transferrable Object Detection |
论文链接 | http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_Scale-Transferrable_Object_Detection_CVPR_2018_paper.pdf |
代码链接 | https://github.com/arvention/STDN |
实验结果
8、W2F
论文 | W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection |
论文链接 | http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_W2F_A_Weakly-Supervised_CVPR_2018_paper.pd |
代码链接 |
|
实验结果
9、
论文 | Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning |
论文链接 | http://openaccess.thecvf.com/content_cvpr_2018/papers/Ge_Multi-Evidence_Filtering_and_CVPR_2018_paper.pdf |
代码链接 |
|
实验结果
10、MELM
论文 | Min-Entropy Latent Model for Weakly Supervised Object Detection |
论文链接 | http://openaccess.thecvf.com/content_cvpr_2018/papers/Wan_Min-Entropy_Latent_Model_CVPR_2018_paper.pdf |
代码链接 | https://github.com/Winfrand/MELM |
实验结果
11、SSM
论文 | Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection |
论文链接 | http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Towards_Human-Machine_Cooperation_CVPR_2018_paper.pdf |
代码链接 | https://github.com/yanxp/SSM-Pytorch |
实验结果
12、
论文 | Feature Selective Networks for Object Detection |
论文链接 | https://arxiv.org/abs/1711.08879 |
代码链接 | https://github.com/robwec/feature-selective-networks |
实验结果
13、PAD
论文 | Pseudo Mask Augmented Object Detection |
论文链接 | http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhao_Pseudo_Mask_Augmented_CVPR_2018_paper.pdf |
代码链接 |
|
实验结果
14、ZLDN
论文 | Zigzag Learning for Weakly Supervised Object Detection |
论文链接 | http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Zigzag_Learning_for_CVPR_2018_paper.pdf |
代码链接 |
|
实验结果
15、
论文 | Learning Globally Optimized Object Detector via Policy Gradient |
论文链接 | http://openaccess.thecvf.com/content_cvpr_2018/papers/Rao_Learning_Globally_Optimized_CVPR_2018_paper.pdf |
代码链接 |
|
实验结果
16、MegDet
论文 | MegDet: A Large Mini-Batch Object Detector |
论文链接 | http://openaccess.thecvf.com/content_cvpr_2018/papers/Peng_MegDet_A_Large_CVPR_2018_paper.pdf |
代码链接 |
|
实验结果
The MegDet is the backbone of our submission (mmAP 52.5%) to COCO 2017 Challenge, where we won the 1st place of Detection task.
17、drl-RPN
论文 | Deep Reinforcement Learning of Region Proposal Networks for Object Detection |
论文链接 | http://openaccess.thecvf.com/content_cvpr_2018/papers/Pirinen_Deep_Reinforcement_Learning_CVPR_2018_paper.pdf |
代码链接 | https://github.com/aleksispi/drl-rpn-tf |
实验结果
18、SIN
论文 | Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships |
论文链接 | http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_Structure_Inference_Net_CVPR_2018_paper.pdf |
代码链接 | https://github.com/choasup/SIN |
实验结果
以下是ECCV2018论文
19、SOD-MTGAN
论文:SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network
论文链接:
http://openaccess.thecvf.com/content_ECCV_2018/papers/Yongqiang_Zhang_SOD-MTGAN_Small_Object_ECCV_2018_paper.pdf
代码链接:
实验结果
20、ML-LocNet
论文:ML-LocNet: Improving Object Localization with Multi-view Learning Network
论文链接:
http://openaccess.thecvf.com/content_ECCV_2018/papers/Xiaopeng_Zhang_ML-LocNet_Improving_Object_ECCV_2018_paper.pdf
代码链接:
实验结果
21、DetNet
论文:DetNet: Design Backbone for Object Detection
论文链接:
http://openaccess.thecvf.com/content_ECCV_2018/papers/Zeming_Li_DetNet_Design_Backbone_ECCV_2018_paper.pdf
代码链接:https://github.com/guoruoqian/DetNet_pytorch
或者https://github.com/BigDeviltjj/mxnet-detnet
实验结果
22、
论文:Weakly Supervised Region Proposal Network and Object Detection
论文链接:
http://openaccess.thecvf.com/content_ECCV_2018/papers/Peng_Tang_Weakly_Supervised_Region_ECCV_2018_paper.pdf
代码链接:
实验结果
23、
论文:Zero-Annotation Object Detection with Web Knowledge Transfer
论文链接:
http://openaccess.thecvf.com/content_ECCV_2018/papers/Qingyi_Tao_Zero-Annotation_Object_Detection_ECCV_2018_paper.pdf
代码链接:
实验结果
24、
论文:Deep Feature Pyramid Reconfiguration for Object Detection
论文链接:
http://openaccess.thecvf.com/content_ECCV_2018/papers/Tao_Kong_Deep_Feature_Pyramid_ECCV_2018_paper.pdf
代码链接:
实验结果
25、RFB-NET
论文:Receptive Field Block Net for Accurate and Fast Object Detection
论文链接:
http://openaccess.thecvf.com/content_ECCV_2018/papers/Songtao_Liu_Receptive_Field_Block_ECCV_2018_paper.pdf
代码链接:https://github.com/ruinmessi/RFBNet
实验结果
26、PFP-NET
论文:Parallel Feature Pyramid Network for Object Detection
论文链接:
http://openaccess.thecvf.com/content_ECCV_2018/papers/Seung-Wook_Kim_Parallel_Feature_Pyramid_ECCV_2018_paper.pdf
代码链接:
实验结果
27、TS2C
论文:TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection
论文链接:
http://openaccess.thecvf.com/content_ECCV_2018/papers/Yunchao_Wei_TS2C_Tight_Box_ECCV_2018_paper.pdf
代码链接:
实验结果
28、SAN
论文:
SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection
论文链接:
http://openaccess.thecvf.com/content_ECCV_2018/papers/Kim_SAN_Learning_Relationship_ECCV_2018_paper.pdf
代码链接:
实验结果
29、
论文:Deep Regionlets for Object Detection
论文链接:
http://openaccess.thecvf.com/content_ECCV_2018/papers/Hongyu_Xu_Deep_Regionlets_for_ECCV_2018_paper.pdf
代码链接:
实验结果
30、
论文:Context Refinement for Object Detection
论文链接:
http://openaccess.thecvf.com/content_ECCV_2018/papers/Zhe_Chen_Context_Refinement_for_ECCV_2018_paper.pdf
代码链接:
实验结果