深度学习完全攻略（连载二十一：目标检测方向深度学习技术路线总结）

Posted 2021-04-19 麻瓜智能

武汉加油

目标检测方向深度学习的主要技术路线图，截止到2019.

https://github.com/hoya012/deep_learning_object_detection

Detector	VOC07 (mAP@IoU=0.5)	VOC12 (mAP@IoU=0.5)	COCO (mAP@IoU=0.5:0.95)	Published In
R-CNN	58.5	-	-	CVPR'14
SPP-Net	59.2	-	-	ECCV'14
MR-CNN	78.2 (07+12)	73.9 (07+12)	-	ICCV'15
Fast R-CNN	70.0 (07+12)	68.4 (07++12)	19.7	ICCV'15
Faster R-CNN	73.2 (07+12)	70.4 (07++12)	21.9	NIPS'15
YOLO v1	66.4 (07+12)	57.9 (07++12)	-	CVPR'16
G-CNN	66.8	66.4 (07+12)	-	CVPR'16
AZNet	70.4	-	22.3	CVPR'16
ION	80.1	77.9	33.1	CVPR'16
HyperNet	76.3 (07+12)	71.4 (07++12)	-	CVPR'16
OHEM	78.9 (07+12)	76.3 (07++12)	22.4	CVPR'16
MPN	-	-	33.2	BMVC'16
SSD	76.8 (07+12)	74.9 (07++12)	31.2	ECCV'16
GBDNet	77.2 (07+12)	-	27.0	ECCV'16
CPF	76.4 (07+12)	72.6 (07++12)	-	ECCV'16
R-FCN	79.5 (07+12)	77.6 (07++12)	29.9	NIPS'16
DeepID-Net	69.0	-	-	PAMI'16
NoC	71.6 (07+12)	68.8 (07+12)	27.2	TPAMI'16
DSSD	81.5 (07+12)	80.0 (07++12)	33.2	arXiv'17
TDM	-	-	37.3	CVPR'17
FPN	-	-	36.2	CVPR'17
YOLO v2	78.6 (07+12)	73.4 (07++12)	-	CVPR'17
RON	77.6 (07+12)	75.4 (07++12)	27.4	CVPR'17
DeNet	77.1 (07+12)	73.9 (07++12)	33.8	ICCV'17
CoupleNet	82.7 (07+12)	80.4 (07++12)	34.4	ICCV'17
RetinaNet	-	-	39.1	ICCV'17
DSOD	77.7 (07+12)	76.3 (07++12)	-	ICCV'17
SMN	70.0	-	-	ICCV'17
Light-Head R-CNN	-	-	41.5	arXiv'17
YOLO v3	-	-	33.0	arXiv'18
SIN	76.0 (07+12)	73.1 (07++12)	23.2	CVPR'18
STDN	80.9 (07+12)	-	-	CVPR'18
RefineDet	83.8 (07+12)	83.5 (07++12)	41.8	CVPR'18
SNIP	-	-	45.7	CVPR'18
Relation-Network	-	-	32.5	CVPR'18
Cascade R-CNN	-	-	42.8	CVPR'18
MLKP	80.6 (07+12)	77.2 (07++12)	28.6	CVPR'18
Fitness-NMS	-	-	41.8	CVPR'18
RFBNet	82.2 (07+12)	-	-	ECCV'18
CornerNet	-	-	42.1	ECCV'18
PFPNet	84.1 (07+12)	83.7 (07++12)	39.4	ECCV'18
Pelee	70.9 (07+12)	-	-	NIPS'18
HKRM	78.8 (07+12)	-	37.8	NIPS'18
M2Det	-	-	44.2	AAAI'19
R-DAD	81.2 (07++12)	82.0 (07++12)	43.1	AAAI'19
ScratchDet	84.1 (07++12)	83.6 (07++12)	39.1	CVPR'19
Libra R-CNN	-	-	43.0	CVPR'19
Reasoning-RCNN	82.5 (07++12)	-	43.2	CVPR'19
FSAF	-	-	44.6	CVPR'19
AmoebaNet + NAS-FPN	-	-	47.0	CVPR'19
Cascade-RetinaNet	-	-	41.1	CVPR'19
TridentNet	-	-	48.4	ICCV'19
DAFS	85.3 (07+12)	83.1 (07++12)	40.5	ICCV'19
Auto-FPN	81.8 (07++12)	-	40.5	ICCV'19
FCOS	-	-	44.7	ICCV'19
FreeAnchor	-	-	44.8	NeurIPS'19
DetNAS	81.5 (07++12)	-	42.0	NeurIPS'19
NATS	-	-	42.0	NeurIPS'19
AmoebaNet + NAS-FPN + AA	-	-	50.7	arXiv'19
EfficientDet	-	-	51.0	arXiv'19

以下是各网络模型的文章

2014年

[R-CNN] Rich feature hierarchies for accurate object detection and semantic segmentation | [CVPR' 14]  [official code - caffe]

 

[OverFeat] OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks | [ICLR' 14]  [official code - torch]

 

[MultiBox] Scalable Object Detection using Deep Neural Networks | [CVPR' 14]

 

[SPP-Net] Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition | [ECCV' 14]  [official code - caffe] [unofficial code - keras] [unofficial code - tensorflow]

 

2015年

Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction | [CVPR' 15]  [official code - matlab]

 

[MR-CNN] Object detection via a multi-region & semantic segmentation-aware CNN model | [ICCV' 15]  [official code - caffe]

 

[DeepBox] DeepBox: Learning Objectness with Convolutional Networks | [ICCV' 15]  [official code - caffe]

 

[AttentionNet] AttentionNet: Aggregating Weak Directions for Accurate Object Detection | [ICCV' 15]

 

[Fast R-CNN] Fast R-CNN | [ICCV' 15]  [official code - caffe]

 

[DeepProposal] DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers | [ICCV' 15]  [official code - matconvnet]

 

[Faster R-CNN, RPN] Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks | [NIPS' 15]  [official code - caffe] [unofficial code - tensorflow] [unofficial code - pytorch]

 

2016年

[YOLO v1] You Only Look Once: Unified, Real-Time Object Detection | [CVPR' 16]  [official code - c]

 

[G-CNN] G-CNN: an Iterative Grid Based Object Detector | [CVPR' 16]

 

[AZNet] Adaptive Object Detection Using Adjacency and Zoom Prediction | [CVPR' 16]

 

[ION] Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks | [CVPR' 16]

 

[HyperNet] HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection | [CVPR' 16]

 

[OHEM] Training Region-based Object Detectors with Online Hard Example Mining | [CVPR' 16]  [official code - caffe]

 

[CRAPF] CRAFT Objects from Images | [CVPR' 16]  [official code - caffe]

 

[MPN] A MultiPath Network for Object Detection | [BMVC' 16]  [official code - torch]

 

[SSD] SSD: Single Shot MultiBox Detector | [ECCV' 16]  [official code - caffe] [unofficial code - tensorflow] [unofficial code - pytorch]

 

[GBDNet] Crafting GBD-Net for Object Detection | [ECCV' 16]  [official code - caffe]

 

[CPF] Contextual Priming and Feedback for Faster R-CNN | [ECCV' 16]

 

[MS-CNN] A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection | [ECCV' 16]  [official code - caffe]

 

[R-FCN] R-FCN: Object Detection via Region-based Fully Convolutional Networks | [NIPS' 16]  [official code - caffe] [unofficial code - caffe]

 

[PVANET] PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection | [NIPSW' 16]  [official code - caffe]

 

[DeepID-Net] DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection | [PAMI' 16]

 

[NoC] Object Detection Networks on Convolutional Feature Maps | [TPAMI' 16]

 

2017年

[DSSD] DSSD : Deconvolutional Single Shot Detector | [arXiv' 17]  [official code - caffe]

 

[TDM] Beyond Skip Connections: Top-Down Modulation for Object Detection | [CVPR' 17]

 

[FPN] Feature Pyramid Networks for Object Detection | [CVPR' 17]  [unofficial code - caffe]

 

[YOLO v2] YOLO9000: Better, Faster, Stronger | [CVPR' 17]  [official code - c] [unofficial code - caffe] [unofficial code - tensorflow] [unofficial code - tensorflow] [unofficial code - pytorch]

 

[RON] RON: Reverse Connection with Objectness Prior Networks for Object Detection | [CVPR' 17]  [official code - caffe] [unofficial code - tensorflow]

 

[RSA] Recurrent Scale Approximation for Object Detection in CNN | | [ICCV' 17]  [official code - caffe]

 

[DCN] Deformable Convolutional Networks | [ICCV' 17]  [official code - mxnet] [unofficial code - tensorflow] [unofficial code - pytorch]

 

[DeNet] DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling | [ICCV' 17]  [official code - theano]

 

[CoupleNet] CoupleNet: Coupling Global Structure with Local Parts for Object Detection | [ICCV' 17]  [official code - caffe]

 

[RetinaNet] Focal Loss for Dense Object Detection | [ICCV' 17]  [official code - keras] [unofficial code - pytorch] [unofficial code - mxnet] [unofficial code - tensorflow]

 

[Mask R-CNN] Mask R-CNN | [ICCV' 17]  [official code - caffe2] [unofficial code - tensorflow] [unofficial code - tensorflow] [unofficial code - pytorch]

 

[DSOD] DSOD: Learning Deeply Supervised Object Detectors from Scratch | [ICCV' 17]  [official code - caffe] [unofficial code - pytorch]

 

[SMN] Spatial Memory for Context Reasoning in Object Detection | [ICCV' 17]

 

[Light-Head R-CNN] Light-Head R-CNN: In Defense of Two-Stage Object Detector | [arXiv' 17]  [official code - tensorflow]

 

[Soft-NMS] Improving Object Detection With One Line of Code | [ICCV' 17]  [official code - caffe]

 

2018年

[YOLO v3] YOLOv3: An Incremental Improvement | [arXiv' 18]  [official code - c] [unofficial code - pytorch] [unofficial code - pytorch] [unofficial code - keras] [unofficial code - tensorflow]

 

[ZIP] Zoom Out-and-In Network with Recursive Training for Object Proposal | [IJCV' 18]  [official code - caffe]

 

[SIN] Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships | [CVPR' 18]  [official code - tensorflow]

 

[STDN] Scale-Transferrable Object Detection | [CVPR' 18]

 

[RefineDet] Single-Shot Refinement Neural Network for Object Detection | [CVPR' 18]  [official code - caffe] [unofficial code - chainer] [unofficial code - pytorch]

 

[MegDet] MegDet: A Large Mini-Batch Object Detector | [CVPR' 18]

 

[DA Faster R-CNN] Domain Adaptive Faster R-CNN for Object Detection in the Wild | [CVPR' 18]  [official code - caffe]

 

[SNIP] An Analysis of Scale Invariance in Object Detection – SNIP | [CVPR' 18]

 

[Relation-Network] Relation Networks for Object Detection | [CVPR' 18]  [official code - mxnet]

 

[Cascade R-CNN] Cascade R-CNN: Delving into High Quality Object Detection | [CVPR' 18]  [official code - caffe]

 

Finding Tiny Faces in the Wild with Generative Adversarial Network | [CVPR' 18]

 

[MLKP] Multi-scale Location-aware Kernel Representation for Object Detection | [CVPR' 18]  [official code - caffe]

 

Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation | [CVPR' 18]  [official code - chainer]

 

[Fitness NMS] Improving Object Localization with Fitness NMS and Bounded IoU Loss | [CVPR' 18]

 

[STDnet] STDnet: A ConvNet for Small Target Detection | [BMVC' 18]

 

[RFBNet] Receptive Field Block Net for Accurate and Fast Object Detection | [ECCV' 18]  [official code - pytorch]

 

Zero-Annotation Object Detection with Web Knowledge Transfer | [ECCV' 18]

 

[CornerNet] CornerNet: Detecting Objects as Paired Keypoints | [ECCV' 18]  [official code - pytorch]

 

[PFPNet] Parallel Feature Pyramid Network for Object Detection | [ECCV' 18]

 

[Softer-NMS] Softer-NMS: Rethinking Bounding Box Regression for Accurate Object Detection | [arXiv' 18]

 

[ShapeShifter] ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector | [ECML-PKDD' 18]  [official code - tensorflow]

 

[Pelee] Pelee: A Real-Time Object Detection System on Mobile Devices | [NIPS' 18]  [official code - caffe]

 

[HKRM] Hybrid Knowledge Routed Modules for Large-scale Object Detection | [NIPS' 18]

 

[MetaAnchor] MetaAnchor: Learning to Detect Objects with Customized Anchors | [NIPS' 18]

 

[SNIPER] SNIPER: Efficient Multi-Scale Training | [NIPS' 18]

 

2019年

[M2Det] M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network | [AAAI' 19] 

 

[R-DAD] Object Detection based on Region Decomposition and Assembly | [AAAI' 19]

 

[CAMOU] CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild | [ICLR' 19]

 

Feature Intertwiner for Object Detection | [ICLR' 19]

 

[GIoU] Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression | [CVPR' 19]

 

Automatic adaptation of object detectors to new domains using self-training | [CVPR' 19]

 

[Libra R-CNN] Libra R-CNN: Balanced Learning for Object Detection | [CVPR' 19]

 

[FSAF] Feature Selective Anchor-Free Module for Single-Shot Object Detection | [CVPR' 19]

 

[ExtremeNet] Bottom-up Object Detection by Grouping Extreme and Center Points | [CVPR' 19]  | [official code - pytorch]

 

[C-MIL] C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection | [CVPR' 19]  | [official code - torch]

 

[ScratchDet] ScratchDet: Training Single-Shot Object Detectors from Scratch | [CVPR' 19]

 

Bounding Box Regression with Uncertainty for Accurate Object Detection | [CVPR' 19]  | [official code - caffe2]

 

Activity Driven Weakly Supervised Object Detection | [CVPR' 19]

 

Towards Accurate One-Stage Object Detection with AP-Loss | [CVPR' 19]

 

Strong-Weak Distribution Alignment for Adaptive Object Detection | [CVPR' 19]  | [official code - pytorch]

 

[NAS-FPN] NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection | [CVPR' 19]

 

[Adaptive NMS] Adaptive NMS: Refining Pedestrian Detection in a Crowd | [CVPR' 19]

 

Point in, Box out: Beyond Counting Persons in Crowds | [CVPR' 19]

 

Locating Objects Without Bounding Boxes | [CVPR' 19]

 

Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects | [CVPR' 19]

 

Towards Universal Object Detection by Domain Attention | [CVPR' 19]

 

Exploring the Bounds of the Utility of Context for Object Detection | [CVPR' 19]

 

What Object Should I Use? - Task Driven Object Detection | [CVPR' 19]

 

Dissimilarity Coefficient based Weakly Supervised Object Detection | [CVPR' 19]

 

Adapting Object Detectors via Selective Cross-Domain Alignment | [CVPR' 19]

 

Fully Quantized Network for Object Detection | [CVPR' 19]

 

Distilling Object Detectors with Fine-grained Feature Imitation | [CVPR' 19]

 

Multi-task Self-Supervised Object Detection via Recycling of Bounding Box Annotations | [CVPR' 19]

 

[Reasoning-RCNN] Reasoning-RCNN: Unifying Adaptive Global Reasoning into Large-scale Object Detection | [CVPR' 19]

 

Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation | [CVPR' 19]

 

Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors | [CVPR' 19]

 

Spatial-aware Graph Relation Network for Large-scale Object Detection | [CVPR' 19]

 

[MaxpoolNMS] MaxpoolNMS: Getting Rid of NMS Bottlenecks in Two-Stage Object Detectors | [CVPR' 19]

 

You reap what you sow: Generating High Precision Object Proposals for Weakly-supervised Object Detection | [CVPR' 19]

 

Object detection with location-aware deformable convolution and backward attention filtering | [CVPR' 19]

 

Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection | [CVPR' 19]

 

[GFR] Improving Object Detection from Scratch via Gated Feature Reuse | [BMVC' 19]  | [official code - pytorch]

 

[Cascade RetinaNet] Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection | [BMVC' 19]

 

Soft Sampling for Robust Object Detection | [BMVC' 19]

 

Multi-adversarial Faster-RCNN for Unrestricted Object Detection | [ICCV' 19]

 

Towards Adversarially Robust Object Detection | [ICCV' 19]

 

A Robust Learning Approach to Domain Adaptive Object Detection | [ICCV' 19]

 

A Delay Metric for Video Object Detection: What Average Precision Fails to Tell | [ICCV' 19]

 

Delving Into Robust Object Detection From Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach | [ICCV' 19]

 

Employing Deep Part-Object Relationships for Salient Object Detection | [ICCV' 19]

 

Learning Rich Features at High-Speed for Single-Shot Object Detection | [ICCV' 19]

 

Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection | [ICCV' 19]

 

Selectivity or Invariance: Boundary-Aware Salient Object Detection | [ICCV' 19]

 

Progressive Sparse Local Attention for Video Object Detection | [ICCV' 19]

 

Minimum Delay Object Detection From Video | [ICCV' 19]

 

Towards Interpretable Object Detection by Unfolding Latent Structures | [ICCV' 19]

 

Scaling Object Detection by Transferring Classification Weights | [ICCV' 19]

 

[TridentNet] Scale-Aware Trident Networks for Object Detection | [ICCV' 19]

 

Generative Modeling for Small-Data Object Detection | [ICCV' 19]

 

Transductive Learning for Zero-Shot Object Detection | [ICCV' 19]

 

Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection | [ICCV' 19]

 

[CenterNet] CenterNet: Keypoint Triplets for Object Detection | [ICCV' 19]

 

[DAFS] Dynamic Anchor Feature Selection for Single-Shot Object Detection | [ICCV' 19]

 

[Auto-FPN] Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification | [ICCV' 19]

 

Multi-Adversarial Faster-RCNN for Unrestricted Object Detection | [ICCV' 19]

 

Object Guided External Memory Network for Video Object Detection | [ICCV' 19]

 

[ThunderNet] ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices | [ICCV' 19]

 

[RDN] Relation Distillation Networks for Video Object Detection | [ICCV' 19]

 

[MMNet] Fast Object Detection in Compressed Video | [ICCV' 19]

 

Towards High-Resolution Salient Object Detection | [ICCV' 19]

 

[SCAN] Stacked Cross Refinement Network for Edge-Aware Salient Object Detection | [ICCV' 19] |[official code]

 

Motion Guided Attention for Video Salient Object Detection | [ICCV' 19]

 

Semi-Supervised Video Salient Object Detection Using Pseudo-Labels | [ICCV' 19]

 

Learning to Rank Proposals for Object Detection | [ICCV' 19]

 

[WSOD2] WSOD2: Learning Bottom-Up and Top-Down Objectness Distillation for Weakly-Supervised Object Detection | [ICCV' 19]

 

[ClusDet] Clustered Object Detection in Aerial Images | [ICCV' 19]

 

Towards Precise End-to-End Weakly Supervised Object Detection Network | [ICCV' 19]

 

Few-Shot Object Detection via Feature Reweighting | [ICCV' 19]

 

[Objects365] Objects365: A Large-Scale, High-Quality Dataset for Object Detection | [ICCV' 19]

 

[EGNet] EGNet: Edge Guidance Network for Salient Object Detection | [ICCV' 19]

 

Optimizing the F-Measure for Threshold-Free Salient Object Detection | [ICCV' 19]

 

Sequence Level Semantics Aggregation for Video Object Detection | [ICCV' 19]

 

[NOTE-RCNN] NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection | [ICCV' 19]

 

Enriched Feature Guided Refinement Network for Object Detection | [ICCV' 19]

 

[POD] POD: Practical Object Detection With Scale-Sensitive Network | [ICCV' 19]

 

[FCOS] FCOS: Fully Convolutional One-Stage Object Detection | [ICCV' 19]

 

[RepPoints] RepPoints: Point Set Representation for Object Detection | [ICCV' 19]

 

Better to Follow, Follow to Be Better: Towards Precise Supervision of Feature Super-Resolution for Small Object Detection | [ICCV' 19]

 

Weakly Supervised Object Detection With Segmentation Collaboration | [ICCV' 19]

 

Leveraging Long-Range Temporal Relationships Between Proposals for Video Object Detection | [ICCV' 19]

 

Detecting 11K Classes: Large Scale Object Detection Without Fine-Grained Bounding Boxes | [ICCV' 19]

 

[C-MIDN] C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object Detection | [ICCV' 19]

 

Meta-Learning to Detect Rare Objects | [ICCV' 19]

 

[Cap2Det] Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection | [ICCV' 19]

 

[Gaussian YOLOv3] Gaussian YOLOv3: An Accurate and Fast Object Detector using Localization Uncertainty for Autonomous Driving | [ICCV' 19]  [official code - c]

 

[FreeAnchor] FreeAnchor: Learning to Match Anchors for Visual Object Detection | [NeurIPS' 19]

 

Memory-oriented Decoder for Light Field Salient Object Detection | [NeurIPS' 19]

 

One-Shot Object Detection with Co-Attention and Co-Excitation | [NeurIPS' 19]

 

[DetNAS] DetNAS: Backbone Search for Object Detection | [NeurIPS' 19]

 

Consistency-based Semi-supervised Learning for Object detection | [NeurIPS' 19]

 

[NATS] Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection | [NeurIPS' 19]

 

[AA] Learning Data Augmentation Strategies for Object Detection | [arXiv' 19]

 

[EfficientDet] EfficientDet: Scalable and Efficient Object Detection | [arXiv' 19]

 

2020年

[Spiking-YOLO] Spiking-YOLO: Spiking Neural Network for Real-time Object Detection | [AAAI' 20]

 

Tell Me What They're Holding: Weakly-supervised Object Detection with Transferable Knowledge from Human-object Interaction | [AAAI' 20]

 

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression | [AAAI' 20]

 

Computation Reallocation for Object Detection | [ICLR' 20]