目标检测-深度学习应用于目标检测的论文

最新推荐文章于 2022-12-29 18:37:29 发布
最新推荐文章于 2022-12-29 18:37:29 发布
阅读量386 收藏 2
点赞数
分类专栏： 目标检测
原文链接：https://github.com/hoya012/deep_learning_object_detection#deep-learning-object-detection
版权

deep learning object detection

A paper list of object detection using deep learning. I wrote this page with reference to this survey paper and searching and searching..

Last updated: 2020/09/22

Update log

2018/9/18 - update all of recent papers and make some diagram about history of object detection using deep learning. 2018/9/26 - update codes of papers. (official and unofficial)
2018/october - update 5 papers and performance table.
2018/november - update 9 papers.
2018/december - update 8 papers and and performance table and add new diagram(2019 version!!).
2019/january - update 4 papers and and add commonly used datasets.
2019/february - update 3 papers.
2019/march - update figure and code links.
2019/april - remove author's names and update ICLR 2019 & CVPR 2019 papers.
2019/may - update CVPR 2019 papers.
2019/june - update CVPR 2019 papers and dataset paper.
2019/july - update BMVC 2019 papers and some of ICCV 2019 papers.
2019/september - update NeurIPS 2019 papers and ICCV 2019 papers.
2019/november - update some of AAAI 2020 papers and other papers.
2020/january - update ICLR 2020 papers and other papers.
2020/may - update CVPR 2020 papers and other papers.
2020/june - update arxiv papers.
2020/august - update paper links.

 

Table of Contents

 

Paper list from 2014 to now(2019)

The part highlighted with red characters means papers that i think "must-read". However, it is my personal opinion and other papers are important too, so I recommend to read them if you have time.

 

Performance table

FPS(Speed) index is related to the hardware spec(e.g. CPU, GPU, RAM, etc), so it is hard to make an equal comparison. The solution is to measure the performance of all models on hardware with equivalent specifications, but it is very difficult and time consuming.

DetectorVOC07 (mAP@IoU=0.5)VOC12 (mAP@IoU=0.5)COCO (mAP@IoU=0.5:0.95)Published In
R-CNN58.5--CVPR'14
SPP-Net59.2--ECCV'14
MR-CNN78.2 (07+12)73.9 (07+12)-ICCV'15
Fast R-CNN70.0 (07+12)68.4 (07++12)19.7ICCV'15
Faster R-CNN73.2 (07+12)70.4 (07++12)21.9NIPS'15
YOLO v166.4 (07+12)57.9 (07++12)-CVPR'16
G-CNN66.866.4 (07+12)-CVPR'16
AZNet70.4-22.3CVPR'16
ION80.177.933.1CVPR'16
HyperNet76.3 (07+12)71.4 (07++12)-CVPR'16
OHEM78.9 (07+12)76.3 (07++12)22.4CVPR'16
MPN--33.2BMVC'16
SSD76.8 (07+12)74.9 (07++12)31.2ECCV'16
GBDNet77.2 (07+12)-27.0ECCV'16
CPF76.4 (07+12)72.6 (07++12)-ECCV'16
R-FCN79.5 (07+12)77.6 (07++12)29.9NIPS'16
DeepID-Net69.0--PAMI'16
NoC71.6 (07+12)68.8 (07+12)27.2TPAMI'16
DSSD81.5 (07+12)80.0 (07++12)33.2arXiv'17
TDM--37.3CVPR'17
FPN--36.2CVPR'17
YOLO v278.6 (07+12)73.4 (07++12)-CVPR'17
RON77.6 (07+12)75.4 (07++12)27.4CVPR'17
DeNet77.1 (07+12)73.9 (07++12)33.8ICCV'17
CoupleNet82.7 (07+12)80.4 (07++12)34.4ICCV'17
RetinaNet--39.1ICCV'17
DSOD77.7 (07+12)76.3 (07++12)-ICCV'17
SMN70.0--ICCV'17
Light-Head R-CNN--41.5arXiv'17
YOLO v3--33.0arXiv'18
SIN76.0 (07+12)73.1 (07++12)23.2CVPR'18
STDN80.9 (07+12)--CVPR'18
RefineDet83.8 (07+12)83.5 (07++12)41.8CVPR'18
SNIP--45.7CVPR'18
Relation-Network--32.5CVPR'18
Cascade R-CNN--42.8CVPR'18
MLKP80.6 (07+12)77.2 (07++12)28.6CVPR'18
Fitness-NMS--41.8CVPR'18
RFBNet82.2 (07+12)--ECCV'18
CornerNet--42.1ECCV'18
PFPNet84.1 (07+12)83.7 (07++12)39.4ECCV'18
Pelee70.9 (07+12)--NIPS'18
HKRM78.8 (07+12)-37.8NIPS'18
M2Det--44.2AAAI'19
R-DAD81.2 (07++12)82.0 (07++12)43.1AAAI'19
ScratchDet84.1 (07++12)83.6 (07++12)39.1CVPR'19
Libra R-CNN--43.0CVPR'19
Reasoning-RCNN82.5 (07++12)-43.2CVPR'19
FSAF--44.6CVPR'19
AmoebaNet + NAS-FPN--47.0CVPR'19
Cascade-RetinaNet--41.1CVPR'19
HTC--47.2CVPR'19
TridentNet--48.4ICCV'19
DAFS85.3 (07+12)83.1 (07++12)40.5ICCV'19
Auto-FPN81.8 (07++12)-40.5ICCV'19
FCOS--44.7ICCV'19
FreeAnchor--44.8NeurIPS'19
DetNAS81.5 (07++12)-42.0NeurIPS'19
NATS--42.0NeurIPS'19
AmoebaNet + NAS-FPN + AA--50.7arXiv'19
SpineNet--52.1arXiv'19
CBNet--53.3AAAI'20
EfficientDet--52.6CVPR'20
DetectoRS--54.7arXiv'20

 

2014

2015

2016

2017

2018

2019

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

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

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

  • Feature Intertwiner for Object Detection | [ICLR' 19] |[pdf]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

  • Locating Objects Without Bounding Boxes | [CVPR' 19] |[pdf]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

  • Hybrid Task Cascade for Instance Segmentation | [CVPR' 19] |[pdf]

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

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

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

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

  • Towards Adversarially Robust Object Detection | [ICCV' 19] |[pdf]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

  • [Spinenet] Spinenet: Learning scale-permuted backbone for recognition and localization | [arXiv' 19] |[pdf]

  • Object Detection in 20 Years: A Survey | [arXiv' 19] |[pdf]

2020

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

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

  • [CBnet] Cbnet: A novel composite backbone network architecture for object detection | [AAAI' 20] |[pdf]

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

  • Computation Reallocation for Object Detection | [ICLR' 20] |[pdf]

  • [YOLOv4] YOLOv4: Optimal Speed and Accuracy of Object Detection | [arXiv' 20] |[pdf]

  • Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector | [CVPR' 20] |[pdf]

  • Large-Scale Object Detection in the Wild From Imbalanced Multi-Labels | [CVPR' 20] |[pdf]

  • Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection | [CVPR' 20] |[pdf]

  • Rethinking Classification and Localization for Object Detection | [CVPR' 20] |[pdf]

  • Multiple Anchor Learning for Visual Object Detection | [CVPR' 20] |[pdf]

  • [CentripetalNet] CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object Detection | [CVPR' 20] |[pdf]

  • Learning From Noisy Anchors for One-Stage Object Detection | [CVPR' 20] |[pdf]

  • [EfficientDet] EfficientDet: Scalable and Efficient Object Detection | [CVPR' 20] |[pdf]

  • Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax | [CVPR' 20] |[pdf]

  • Dynamic Refinement Network for Oriented and Densely Packed Object Detection | [CVPR' 20] |[pdf]

  • Noise-Aware Fully Webly Supervised Object Detection | [CVPR' 20] |[pdf]

  • [Hit-Detector] Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection | [CVPR' 20] |[pdf]

  • [D2Det] D2Det: Towards High Quality Object Detection and Instance Segmentation | [CVPR' 20] |[pdf]

  • Prime Sample Attention in Object Detection | [CVPR' 20] |[pdf]

  • Don’t Even Look Once: Synthesizing Features for Zero-Shot Detection | [CVPR' 20] |[pdf]

  • Exploring Categorical Regularization for Domain Adaptive Object Detection | [CVPR' 20] |[pdf]

  • [SP-NAS] SP-NAS: Serial-to-Parallel Backbone Search for Object Detection | [CVPR' 20] |[pdf]

  • [NAS-FCOS] NAS-FCOS: Fast Neural Architecture Search for Object Detection | [CVPR' 20] |[pdf]

  • [DR Loss] DR Loss: Improving Object Detection by Distributional Ranking | [CVPR' 20] |[pdf]

  • Detection in Crowded Scenes: One Proposal, Multiple Predictions | [CVPR' 20] |[pdf]

  • [AugFPN] AugFPN: Improving Multi-Scale Feature Learning for Object Detection | [CVPR' 20] |[pdf]

  • Robust Object Detection Under Occlusion With Context-Aware CompositionalNets | [CVPR' 20] |[pdf]

  • Cross-Domain Document Object Detection: Benchmark Suite and Method | [CVPR' 20] |[pdf]

  • Exploring Bottom-Up and Top-Down Cues With Attentive Learning for Webly Supervised Object Detection | [CVPR' 20] |[pdf]

  • [SLV] SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection | [CVPR' 20] |[pdf]

  • [HAMBox] HAMBox: Delving Into Mining High-Quality Anchors on Face Detection | [CVPR' 20] |[pdf]

  • [Context R-CNN] Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection | [CVPR' 20] |[pdf]

  • Mixture Dense Regression for Object Detection and Human Pose Estimation | [CVPR' 20] |[pdf]

  • Offset Bin Classification Network for Accurate Object Detection | [CVPR' 20] |[pdf]

  • [NETNet] NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection | [CVPR' 20] |[pdf]

  • Scale-Equalizing Pyramid Convolution for Object Detection | [CVPR' 20] |[pdf]

  • Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians | [CVPR' 20] |[pdf]

  • [MnasFPN] MnasFPN: Learning Latency-Aware Pyramid Architecture for Object Detection on Mobile Devices | [CVPR' 20] |[pdf]

  • Physically Realizable Adversarial Examples for LiDAR Object Detection | [CVPR' 20] |[pdf]

  • Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation | [CVPR' 20] |[pdf]

  • Incremental Few-Shot Object Detection | [CVPR' 20] |[pdf]

  • Where, What, Whether: Multi-Modal Learning Meets Pedestrian Detection | [CVPR' 20] |[pdf]

  • Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation | [CVPR' 20] |[pdf]

  • Learning a Unified Sample Weighting Network for Object Detection | [CVPR' 20] |[pdf]

  • Seeing without Looking: Contextual Rescoring of Object Detections for AP Maximization | [CVPR' 20] |[pdf]

  • DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution | [arXiv' 20] |[pdf]

  • [DETR] End-to-End Object Detection with Transformers | [ECCV' 20] |[pdf]

  • Suppress and Balance: A Simple Gated Network for Salient Object Detection | [ECCV' 20] |[code]

  • [BorderDet] BorderDet: Border Feature for Dense Object Detection | [ECCV' 20] |[pdf]

  • Corner Proposal Network for Anchor-free, Two-stage Object Detection | [ECCV' 20] |[pdf]

  • A General Toolbox for Understanding Errors in Object Detection | [ECCV' 20] |[pdf]

  • [Chained-Tracker] Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking | [ECCV' 20] |[pdf]

  • Side-Aware Boundary Localization for More Precise Object Detection | [ECCV' 20] |[pdf]

  • [PIoU] PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments | [ECCV' 20] |[pdf]

  • [AABO] AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling | [ECCV' 20] |[pdf]

  • Highly Efficient Salient Object Detection with 100K Parameters | [ECCV' 20] |[pdf]

  • [GeoGraph] GeoGraph: Learning graph-based multi-view object detection with geometric cues end-to-end | [ECCV' 20] |[pdf]

  • Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection| [ECCV' 20] |[pdf]

  • Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection | [ECCV' 20] |[pdf]

  • Arbitrary-Oriented Object Detection with Circular Smooth Label | [ECCV' 20] |[pdf]

  • Soft Anchor-Point Object Detection | [ECCV' 20] |[pdf]

  • Object Detection with a Unified Label Space from Multiple Datasets | [ECCV' 20] |[pdf]

  • [MimicDet] MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection | [ECCV' 20] |[pdf]

  • Prior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions | [ECCV' 20] |[pdf]

  • [Dynamic R-CNN] Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training | [ECCV' 20] |[pdf]

  • [OS2D] OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features | [ECCV' 20] |[pdf]

  • Multi-Scale Positive Sample Refinement for Few-Shot Object Detection | [ECCV' 20] |[pdf]

  • Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild | [ECCV' 20] |[pdf]

  • Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection | [ECCV' 20] |[pdf]

  • Two-Stream Active Query Suggestion for Large-Scale Object Detection in Connectomics | [ECCV' 20] |[pdf]

  • [FDTS] FDTS: Fast Diverse-Transformation Search for Object Detection and Beyond | [ECCV' 20]

  • Dual refinement underwater object detection network | [ECCV' 20] |[pdf]

  • [APRICOT] APRICOT: A Dataset of Physical Adversarial Attacks on Object Detection | [ECCV' 20] |[pdf]

  • Large Batch Optimization for Object Detection: Training COCO in 12 Minutes | [ECCV' 20] |[pdf]

  • Hierarchical Context Embedding for Region-based Object Detection | [ECCV' 20] |[pdf]

  • Pillar-based Object Detection for Autonomous Driving | [ECCV' 20] |[pdf]

  • Dive Deeper Into Box for Object Detection | [ECCV' 20] |[pdf]

  • Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN | [ECCV' 20] |[pdf]

  • Probabilistic Anchor Assignment with IoU Prediction for Object Detection | [ECCV' 20] |[pdf]

  • [HoughNet] HoughNet: Integrating near and long-range evidence for bottom-up object detection | [ECCV' 20] |[pdf]

  • [LabelEnc] LabelEnc: A New Intermediate Supervision Method for Object Detection | [ECCV' 20] |[pdf]

  • Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer | [ECCV' 20] |[pdf]

  • On the Importance of Data Augmentation for Object Detection | [ECCV' 20] |[[pdf]]

  • Adaptive Object Detection with Dual Multi-Label Prediction | [ECCV' 20] |[pdf]

  • Quantum-soft QUBO Suppression for Accurate Object Detection | [ECCV' 20] |[pdf]

  • Improving Object Detection with Selective Self-supervised Self-training | [ECCV' 20] |[pdf]

 

Dataset Papers

Statistics of commonly used object detection datasets. The Table came from this survey paper.

ChallengeObject ClassesNumber of ImagesNumber of Annotated Images
TrainValTestTrainVal
PASCAL VOC Object Detection Challenge
VOC07202,5012,5104,9526,301 (7,844)6,307 (7,818)
VOC08202,1112,2214,1335,082 (6,337)5,281 (6,347)
VOC09203,4733,5816,6508,505 (9,760)8,713 (9,779)
VOC10204,9985,1059,63711,577 (13,339)11,797 (13,352)
VOC11205,7175,82310,99413,609 (15,774)13,841 (15,787)
VOC12205,7175,82310,99113,609 (15,774)13,841 (15,787)
ILSVRC Object Detection Challenge
ILSVRC13200395,90920,12140,152345,85455,502
ILSVRC14200456,56720,12140,152478,80755,502
ILSVRC15200456,56720,12151,294478,80755,502
ILSVRC16200456,56720,12160,000478,80755,502
ILSVRC17200456,56720,12165,500478,80755,502
MS COCO Object Detection Challenge
MS COCO158082,78340,50481,434604,907291,875
MS COCO168082,78340,50481,434604,907291,875
MS COCO1780118,2875,00040,670860,00136,781
MS COCO1880118,2875,00040,670860,00136,781
Open Images Object Detection Challenge
OID185001,743,04241,620125,43612,195,144―

The papers related to datasets used mainly in Object Detection are as follows.

  • [PASCAL VOC] The PASCAL Visual Object Classes (VOC) Challenge | [IJCV' 10] | [pdf]

  • [PASCAL VOC] The PASCAL Visual Object Classes Challenge: A Retrospective | [IJCV' 15] | [pdf] | [link]

  • [ImageNet] ImageNet: A Large-Scale Hierarchical Image Database| [CVPR' 09] | [pdf]

  • [ImageNet] ImageNet Large Scale Visual Recognition Challenge | [IJCV' 15] | [pdf] | [link]

  • [COCO] Microsoft COCO: Common Objects in Context | [ECCV' 14] | [pdf] | [link]

  • [Open Images] The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale | [arXiv' 18] | [pdf] | [link]

  • [DOTA] DOTA: A Large-scale Dataset for Object Detection in Aerial Images | [CVPR' 18] | [pdf] | [link]

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

 

Contact & Feedback

If you have any suggestions about papers, feel free to mail me :)

shanzsz
关注
专栏目录
深度学习在目标检测方面的应用论文
01-18
附件中包含5篇深度学习在目标检测方面的论文，全英文文章
目标检测-20种常用深度学习算法论文、复现代码汇总.zip
03-29
目标检测-20种常用深度学习算法论文、复现代码汇总
目标检测论文整理
weixin_30292745的博客
06-30 207
最近开始看一些object detection的文章，顺便整理一下思路。排版比较乱，而且几乎所有图片都是应用的博客或论文，如有侵权请联系我。 文章阅读路线参考 目前已完成的文章如下，后续还会继续补充（其中加粗的为精读文章）： RCNN Overfeat MR-CNN SPPNet Fast RCNN A Fast RCNN Faster RCNN FPN R-FCN Mask RCNN YOLO...
深度学习论文阅读目标检测篇（六）中英对照版：YOLOv3《 An Incremental Improvement》
与君共勉，一起学习
06-07 1366
  We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that’s pretty swell. It’s a little bigger than last time but more accurate. It’s still fast though, don’t worry. At 320×320 YOLO
人工智能-目标检测-基于深度学习的快速目标检测技术研究.pdf
06-26
《基于深度学习的快速目标检测技术研究》这篇论文主要探讨了如何利用深度学习技术改进目标检测的效率和实时性，特别是在解决模型复杂度高、计算量大等问题上的创新方法。 一、深度学习与目标检测 深度学习是近年来...
人工智能-目标检测-基于深度学习的鱼眼图像目标检测研究.pdf
06-26
【鱼眼图像与深度学习目标检测】\n\n鱼眼图像是一种特殊类型的图像，由超广角鱼眼镜头拍摄，其显著特征是拥有极大的视角，能够捕捉到比普通镜头更广阔的场景。这种特性使得鱼眼图像在多个领域，如视频监控、安全监控...
基于深度学习的目标检测框架介绍.ppt
05-08
【基于深度学习的目标检测框架介绍】 目标检测是计算机视觉领域中的一个重要任务，它结合了图像分类和物体定位的功能。与传统的深度学习算法主要关注单一类别识别不同，目标检测旨在识别图像中的多个对象并精确地...
目标检测（深度学习）相关论文
03-06
内含近年深度学习领域目标检测论文，包括faster rcnn，yolo，yolo9000，ssd，mask rcnn等
精品--深度学习总结，包含基础知识、目标检测、目标跟踪、目标分类，深度学习八股文，相关竞赛等.zip
最新发布
02-05
目标检测是深度学习在计算机视觉中的重要应用，涉及到识别图像中的特定对象并定位其位置。常见的目标检测框架有YOLO（You Only Look Once）、SSD（Single Shot MultiBox Detector）和Faster R-CNN等。这些方法通常...
深度学习目标检测论文
12-09
基于深度学习的目标检测论文包括faster RCNN，SSD, YOLO,Mask RCNN等等，以及各种网络论文：LeNet，AlexNet、vgg，ResNet等等
[论文解读]Deep active learning for object detection
年糕的博客
09-22 1390
Deep active learning for object detection 文章目录Deep active learning for object detection简介摘要初步以前的工作Method黑箱主动学习3.1.1 Minmax (mm)3.1.2 Maximum Entropy (ent)3.1.3 Sum Entropy (ent-sum)白盒主动学习勘探/开发框架结果PASCAL VOC不同口味白盒的比较与黑箱方法的比较勘探/开发方法比较使用35%图像的不同方法的mapKitti模型分
深度学习目标检测的论文集及概述
xiaobaizaza_Ry的博客
08-16 2180
deep learning object detection A paper list of object detection using deep learning. I wrote this page with reference to this survey paper and searching and searching.. Last updated: 2020/07/17 Update log 2018/9/18 - update all of recent papers an...
深度学习目标检测系列论文阅读和Pytorch实现(一)
IEEE_FELLOW的博客
01-20 715
深度学习中目标检测通常分单阶段和两阶段算法。这里整理最近研究的单阶段系列算法，包含论文的简单介绍和Pytorch代码实现。 算法路线为SSD=>FPN=>RetinaNet=>EfficientDet. 目前正在复现EfficientDet论文。 1、SSD论文解读 2、SSD算法实现和训练自己的数据集 3、FPN论文解读：https://blog.csdn.net/I...
基于faster-rcnn的文本图像中的表格检测
zshluckydogs的博客
06-25 3473
前言： 在对文本图像进行分析时，除了常规的ocr之外如果文本中有表格结构如何同时对表格区域的文本部分进行ocr并且保留表格的结构是一个非常迫切而又实际的需求。然而，关于文本表格分析方面的资源却比较稀缺，博主搜寻了很长时间也不过找到几篇论文以及效果不怎么样的OpenCV方法，秉持着自己动手丰衣足食的想法博主走上了看论文写代码的不归路，这期间是怎样的惊心动魄、扣人心弦就不详细记录了，虽然最终的结果不...
目标检测相关论文和代码资源汇总
风信子的猫Redamancy的快乐星球
07-30 5420
目标检测相关论文和代码资源汇总 文章目录目标检测相关论文和代码资源汇总2014～2019模型汇总（红色为推荐必读篇）：Performance table 性能表2014论文及代码2015论文及代码2016论文及代码2017论文及代码2018论文及代码2019论文及代码2020论文及代码Dataset Papers 常用的目标检测数据集 2014～2019模型汇总（红色为推荐必读篇）： Performance table 性能表 FPS(Speed) index is related to the hard
用于表检测和结构识别的深度学习：综述
jyjy0608的博客
12-29 2759
Deep learning for table detection and structure recognition: A survey
目标检测综述：基于至今先进深度学习的目标检测模型综述（附综述论文及代码下载）...
gzq0723的博客
08-27 882
关注并星标从此不迷路计算机视觉研究院公众号ID｜ComputerVisionGzq学习群｜扫码在主页获取加入方式论文地址：https://arxiv.org/pdf/2104.11892.pdf计算机视觉研究院专栏作者：Edison_G目标检测是对图像或视频中的目标进行分类和定位的任务。由于其广泛的应用，近年来它已获得突出地位。01概述今天分享中我们调查了基于深度学习的目标检测器的最新发展。还...
2021-IEEE论文-深度神经网络在文档图像表格识别中的应用现状及性能分析
jyjy0608的博客
05-13 4895
2021年5月12日收到， 2021年6月4日接受， 出版日期2021年6月9日， 当前版本日期2021年6月24日。 摘要 - Abstract   表格识别的第一阶段是检测文档中的表格区域。随后，在第二阶段识别表格结构，以便从各个单元中提取信息。表格检测和结构识别是表格理解领域的关键问题。然而，由于表格中存在大量的多样性和不对称性，导致了表格分析是一项复杂的任务，因此它是文档图像分析中一个活跃的研究领域。图形处理单元计算能力的最新进展使深度神经网络的性能优于传统的最先进的机器学习方法。表格理解从深度
年度总结 | 目标检测2019，你还有不知道的吗？
gzq0723的博客
01-19 3890
新年焕新2019年感谢你们和“计算机视觉战队”一起度过。这一年我们又加入了上万的学习爱好者和我们一起技术交流，感谢大家的支持，也感谢大家在学习群里的热火交流，感谢一致的关注和陪伴，接下来...
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值