Object Detection目標檢測全面總結--重要
原地址:https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html
Object Detection
Published: 09 Oct 2015 Category:Method | VOC2007 | VOC2010 | VOC2012 | ILSVRC 2013 | MSCOCO 2015 | Speed |
---|---|---|---|---|---|---|
OverFeat | 24.3% | |||||
R-CNN (AlexNet) | 58.5% | 53.7% | 53.3% | 31.4% | ||
R-CNN (VGG16) | 66.0% | |||||
SPP_net(ZF-5) | 54.2%(1-model), 60.9%(2-model) | 31.84%(1-model), 35.11%(6-model) | ||||
DeepID-Net | 64.1% | 50.3% | ||||
NoC | 73.3% | 68.8% | ||||
Fast-RCNN (VGG16) | 70.0% | 68.8% | 68.4% | 19.7%(@[0.5-0.95]), 35.9%(@0.5) | ||
MR-CNN | 78.2% | 73.9% | ||||
Faster-RCNN (VGG16) | 78.8% | 75.9% | 21.9%(@[0.5-0.95]), 42.7%(@0.5) | 198ms | ||
Faster-RCNN (ResNet-101) | 85.6% | 83.8% | 37.4%(@[0.5-0.95]), 59.0%(@0.5) | |||
YOLO | 63.4% | 57.9% | 45 fps | |||
YOLO VGG-16 | 66.4% | 21 fps | ||||
YOLOv2 544 × 544 | 78.6% | 73.4% | 21.6%(@[0.5-0.95]), 44.0%(@0.5) | 40 fps | ||
SSD300 (VGG16) | 77.2% | 75.8% | 25.1%(@[0.5-0.95]), 43.1%(@0.5) | 46 fps | ||
SSD512 (VGG16) | 79.8% | 78.5% | 28.8%(@[0.5-0.95]), 48.5%(@0.5) | 19 fps | ||
ION | 79.2% | 76.4% | ||||
CRAFT | 75.7% | 71.3% | 48.5% | |||
OHEM | 78.9% | 76.3% | 25.5%(@[0.5-0.95]), 45.9%(@0.5) | |||
R-FCN (ResNet-50) | 77.4% | 0.12sec(K40), 0.09sec(TitianX) | ||||
R-FCN (ResNet-101) | 79.5% | 0.17sec(K40), 0.12sec(TitianX) | ||||
R-FCN (ResNet-101),multi sc train | 83.6% | 82.0% | 31.5%(@[0.5-0.95]), 53.2%(@0.5) | |||
PVANet 9.0 | 89.8% | 84.2% | 750ms(CPU), 46ms(TitianX) |
Papers
Deep Neural Networks for Object Detection
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
R-CNN
Rich feature hierarchies for accurate object detection and semantic segmentation
Fast R-CNN
Fast R-CNN
A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
Faster R-CNN
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
R-CNN minus R
Faster R-CNN in MXNet with distributed implementation and data parallelization
Contextual Priming and Feedback for Faster R-CNN
An Implementation of Faster RCNN with Study for Region Sampling
Interpretable R-CNN
- intro: North Carolina State University & Alibaba
- keywords: AND-OR Graph (AOG)
Light-Head R-CNN
Light-Head R-CNN: In Defense of Two-Stage Object Detector
Cascade R-CNN
Cascade R-CNN: Delving into High Quality Object Detection
MultiBox
Scalable Object Detection using Deep Neural Networks
Scalable, High-Quality Object Detection
SPP-Net
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
DeepID-Net
DeepID-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
MR-CNN
Object detection via a multi-region & semantic segmentation-aware CNN model
YOLO
You Only Look Once: Unified, Real-Time Object Detection
darkflow - translate darknet to tensorflow. Load trained weights, retrain/fine-tune them using tensorflow, export constant graph def to C++
Start Training YOLO with Our Own Data
YOLO: Core ML versus MPSNNGraph
TensorFlow YOLO object detection on Android
- intro: Real-time object detection on Android using the YOLO network with TensorFlow
Computer Vision in iOS – Object Detection
YOLOv2
YOLO9000: Better, Faster, Stronger
Yolo_mark: GUI for marking bounded boxes of objects in images for training Yolo v2
LightNet: Bringing pjreddie’s DarkNet out of the shadows
AttentionNet: Aggregating Weak Directions for Accurate Object Detection
DenseBox
DenseBox: Unifying Landmark Localization with End to End Object Detection
SSD
SSD: Single Shot MultiBox Detector
What’s the diffience in performance between this new code you pushed and the previous code? #327
Enhancement of SSD by concatenating feature maps for object detection
DSSD
DSSD : Deconvolutional Single Shot Detector
Context-aware Single-Shot Detector
- keywords: CSSD, DiCSSD, DeCSSD, effective receptive fields (ERFs), theoretical receptive fields (TRFs)
Feature-Fused SSD: Fast Detection for Small Objects
FSSD
FSSD: Feature Fusion Single Shot Multibox Detector
Inside-Outside Net (ION)
Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
Adaptive Object Detection Using Adjacency and Zoom Prediction
G-CNN: an Iterative Grid Based Object Detector
Factors in Finetuning Deep Model for object detection
Factors in Finetuning Deep Model for Object Detection with Long-tail Distribution
We don’t need no bounding-boxes: Training object class detectors using only human verification
HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
A MultiPath Network for Object Detection
CRAFT
CRAFT Objects from Images
OHEM
Training Region-based Object Detectors with Online Hard Example Mining
S-OHEM: Stratified Online Hard Example Mining for Object Detection
Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers
- intro: CVPR 2016
- keywords: scale-dependent pooling (SDP), cascaded rejection classifiers (CRC)
R-FCN
R-FCN: Object Detection via Region-based Fully Convolutional Networks
R-FCN-3000 at 30fps: Decoupling Detection and Classification
Recycle deep features for better object detection
MS-CNN
A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
Multi-stage Object Detection with Group Recursive Learning
Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection
PVANET
PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection
PVANet: Lightweight Deep Neural Networks for Real-time Object Detection
- intro: Presented at NIPS 2016 Workshop on Efficient Methods for Deep Neural Networks (EMDNN). Continuation of arXiv:1608.08021
GBD-Net
Gated Bi-directional CNN for Object Detection
Crafting GBD-Net for Object Detection
- intro: winner of the ImageNet object detection challenge of 2016. CUImage and CUVideo
- intro: gated bi-directional CNN (GBD-Net)
StuffNet
StuffNet: Using ‘Stuff’ to Improve Object Detection
Generalized Haar Filter based Deep Networks for Real-Time Object Detection in Traffic Scene
Hierarchical Object Detection with Deep Reinforcement Learning
Learning to detect and localize many objects from few examples
Speed/accuracy trade-offs for modern convolutional object detectors
SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving
Feature Pyramid Network (FPN)
Feature Pyramid Networks for Object Detection
Action-Driven Object Detection with Top-Down Visual Attentions
Beyond Skip Connections: Top-Down Modulation for Object Detection
Wide-Residual-Inception Networks for Real-time Object Detection
Attentional Network for Visual Object Detection
- intro: University of Maryland & Mitsubishi Electric Research Laboratories
Learning Chained Deep Features and Classifiers for Cascade in Object Detection
- keykwords: CC-Net
- intro: chained cascade network (CC-Net). 81.1% mAP on PASCAL VOC 2007
DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling
Discriminative Bimodal Networks for Visual Localization and Detection with Natural Language Queries
Spatial Memory for Context Reasoning in Object Detection
Accurate Single Stage Detector Using Recurrent Rolling Convolution
Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection
LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems
- intro: Embedded Vision Workshop in CVPR. UC San Diego & Qualcomm Inc
Point Linking Network for Object Detection
Perceptual Generative Adversarial Networks for Small Object Detection
Few-shot Object Detection
Yes-Net: An effective Detector Based on Global Information
SMC Faster R-CNN: Toward a scene-specialized multi-object detector
Towards lightweight convolutional neural networks for object detection
RON: Reverse Connection with Objectness Prior Networks for Object Detection
Mimicking Very Efficient Network for Object Detection
Residual Features and Unified Prediction Network for Single Stage Detection
Deformable Part-based Fully Convolutional Network for Object Detection
- intro: BMVC 2017 (oral). Sorbonne Universités & CEDRIC
Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors
Recurrent Scale Approximation for Object Detection in CNN
DSOD
DSOD: Learning Deeply Supervised Object Detectors from Scratch
Focal Loss for Dense Object Detection
- intro: ICCV 2017 Best student paper award. Facebook AI Research
- keywords: RetinaNet
CoupleNet: Coupling Global Structure with Local Parts for Object Detection
Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection
StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection
Dynamic Zoom-in Network for Fast Object Detection in Large Images
Zero-Annotation Object Detection with Web Knowledge Transfer
- intro: NTU, Singapore & Amazon
- keywords: multi-instance multi-label domain adaption learning framework
MegDet
MegDet: A Large Mini-Batch Object Detector
- intro: Peking University & Tsinghua University & Megvii Inc
Single-Shot Refinement Neural Network for Object Detection
Receptive Field Block Net for Accurate and Fast Object Detection
An Analysis of Scale Invariance in Object Detection - SNIP
Feature Selective Networks for Object Detection
Learning a Rotation Invariant Detector with Rotatable Bounding Box
Scalable Object Detection for Stylized Objects
Relation Networks for Object Detection
Learning Object Detectors from Scratch with Gated Recurrent Feature Pyramids
Deep Regionlets for Object Detection
- keywords: region selection network, gating network
Adversarial Examples that Fool Detectors
NMS
End-to-End Integration of a Convolutional Network, Deformable Parts Model and Non-Maximum Suppression
A convnet for non-maximum suppression
Improving Object Detection With One Line of Code
Soft-NMS – Improving Object Detection With One Line of Code
Learning non-maximum suppression
Weakly Supervised Object Detection
Track and Transfer: Watching Videos to Simulate Strong Human Supervision for Weakly-Supervised Object Detection
Weakly supervised object detection using pseudo-strong labels
Saliency Guided End-to-End Learning for Weakly Supervised Object Detection
Detection From Video
Learning Object Class Detectors from Weakly Annotated Video
Analysing domain shift factors between videos and images for object detection
Video Object Recognition
Deep Learning for Saliency Prediction in Natural Video