地平線黃李超開講:深度學習和物體檢測!
對話CVPR2016:目標檢測新進展:
基於深度學習的目標檢測技術演進:R-CNN、Fast R-CNN、Faster R-CNN:
基於深度學習的目標檢測研究進展
講堂幹貨No.1|山世光-基於深度學習的目標檢測技術進展與展望
基於特征共享的高效物體檢測 Faster R-CNN和ResNet的作者任少卿 博士畢業論文 中文
R-CNN:論文筆記
Fast-RCNN:
Faster-RCNN:
FPN:
R-FCN:
SSD:
YOLO:
DenseBox:餘凱特邀報告:基於密集預測圖的物體檢測技術造就全球領先的ADAS係統
PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection - [http://www.cnblogs.com/xueyuxiaolang/p/5959442.html]
深度學習論文筆記:DSSD - [https://jacobkong.github.io/blog/2938514597/]
DSOD
Focal Loss:
Soft-NMS:
OHEM:
Mask-RCNN 2017:
目標檢測之比較
視覺目標檢測和識別之過去,現在及可能
CVPR2019目標檢測方法進展綜述
基於深度學習的「目標檢測」算法綜述
目標檢測綜述
深度學習目標檢測網絡彙總對比
從錨點到關鍵點,最新的目標檢測方法發展到哪了
從RCNN到SSD,這應該是最全的一份目標檢測算法盤點
目標檢測中的不平衡問題:綜述
深度學習中用於對象檢測的最新進展
基於深度學習的對象檢測概述
目標檢測20年:綜述
Deep Neural Networks for Object Detection (基於DNN的對象檢測)NIPS2013:
R-CNNRich feature hierarchies for accurate object detection and semantic segmentation:
Fast R-CNN:
Faster R-CNNFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks:
Mask R-CNN
Light-Head R-CNN
Cascade R-CNN
Scalable Object Detection using Deep Neural Networks
Scalable, High-Quality Object Detection
SPP-NetSpatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
DeepID-NetDeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
Object Detectors Emerge in Deep Scene CNNs
segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection
Object Detection Networks on Convolutional Feature Maps
Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
DeepBox: Learning Objectness with Convolutional Networks
Object detection via a multi-region & semantic segmentation-aware CNN model
You Only Look Once: Unified, Real-Time Object Detection
YOLOv2 YOLO9000: Better, Faster, Stronger
YOLOv3
YOLT
AttentionNet: Aggregating Weak Directions for Accurate Object Detection
DenseBox: Unifying Landmark Localization with End to End Object Detection
SSD: Single Shot MultiBox Detector
DSSD : Deconvolutional Single Shot Detector
FSSD
ESSD
MDSSD
Pelee
Fire SSD
G-CNN: an Iterative Grid Based Object Detector
HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
A MultiPath Network for Object Detection
R-FCN: Object Detection via Region-based Fully Convolutional Networks
A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection
Feature Pyramid Networks for Object Detection
Learning Chained Deep Features and Classifiers for Cascade in Object Detection
DSOD: Learning Deeply Supervised Object Detectors from Scratch
Focal Loss for Dense Object Detection ICCV 2017 Best student paper award. Facebook AI Research
MegDet
Mask-RCNN 2017 ICCV 2017 Best paper award. Facebook AI Research
RefineNet
DetNet
SSOD
CornerNet
M2Det
3D Object Detection
ZSD(Zero-Shot Object Detection)
OSD(One-Shot object Detection)
Weakly Supervised Object Detection
Softer-NMS
NAS-FPN,可實現比Mask-RCNN、FPN、SSD更快更好的目標檢測
多方向目標檢測:水平邊界框上的滑動頂點
SM-NAS:結構到模塊的神經體係結構搜索以進行目標檢測
基於PSNet和邊框回歸的弱監督目標檢測(WSOD)
帶有可見IoU和Box Sign預測器的遮擋性行人檢測
CSPNet:可以增強CNN學習能力的新型Backbone
ReBiF:殘差雙融合特征金字塔網絡,用於較精確的Single-shot目標檢測
目標檢測的性能上界討論
DIoU Loss:更快更好地學習邊界框回歸
CoAE:用於One-Shot目標檢測的共同注意和共同激勵
SAPD:Soft Anchor-Point目標檢測
MMOD:基於混合模型的目標檢測邊界框密度估計
IENet:方向性航空目標檢測的One Stage Anchor Free檢測器
MnasFPN:用於移動設備上目標檢測的延遲感知的金字塔體係結構
IPG-Net:用於目標檢測的圖像金字塔引導網絡
MAL:用於目標檢測的多Anchor學習
ATSS:縮小Anchor-free和Anchor-based的性能差距:通過自適應訓練樣本選擇
Strong-Weak Distribution Alignment for Adaptive Object Detection
PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation
Deep HoughVoting for 3D Object Detection in Point Clouds
Simultaneous multi-view instance detection with learned geometric soft-constraints
Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
Towards Adversarially Robust Object Detection
Multi-adversarial Faster-RCNN for Unrestricted Object Detection
Selectivity or Invariance: Boundary-aware Salient Object Detection
Joint Monocular 3D Detection and Tracking
GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition
ThunderNet: Towards Real-time Generic Object Detection
MemorizingNormality to Detect Anomaly: Memory-augmented Deep Autoencoder (MemAE) forUnsupervised Anomaly Detection
R-CNN
Fast R-CNN:
Faster R-CNN
SPP-Net
YOLO
YOLOv2
YOLOv3
SSD
Recurrent Scale Approximation for Object Detection in CNN
Mask-RCNN 2017
Light-Head R-CNN
Cascade R-CNN
YOLT
DSSD
Pelee
R-FCN
FPN
DSOD
RetinaNet
MegDet
RefineNet
DetNet
CornerNet
M2Det
3D Object Detection
Softer-NMS
初步版本,水平有限,有錯誤或者不完善的地方,歡迎大家提建議和補充,會一直保持更新,本文為專知內容組原創內容,未經允許不得轉載,如需轉載請發送郵件至fangquanyi@gmail.com或 聯係微信專知小助手(Rancho_Fang)
敬請關注//www.webtourguide.com和關注專知公眾號,獲取第一手AI相關知識
最近更新:2019-12-10