机器学习和深度学习资源汇总(陆续更新)

转载:https://www.cnblogs.com/zlslch/p/6970680.html

不多说,直接上干货! 

    本篇博客的目地,是对工作学习过程中所遇所见的一些有关深度学习、机器学习的优质资源,作分类汇总,方便自己查阅,也方便他人学习借用。

    主要会涉及一些优质的理论书籍和论文、一些实惠好用的工具库和开源库、一些供入门该理论入门所用的demo等等。

    由于本博客将不定期更新,尽量将较为前沿的深度学习、机器学习内容整理下来,需要转载的同学尽量附上本文的链接,方便获得最新的内容。

 

 

 

机器学习领域相关的大牛推荐(陆续更新)

 

 

  • 相关的理论、书籍、论文、课程、博客:
    • [Book] Yoshua Bengio, Ian Goodfellow, Aaron Courville. Deep Learning. 2015.

 

 

 

  • 相关的库、工具
    • Caffe (C++, with Python wrapper)

 

 

  • 相关的开源项目、demo
 
 
 

 

 

 

 

MethodVOC2007VOC2010VOC2012ILSVRC 2013MSCOCO 2015Speed
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-Net64.1%  50.3%  
NoC73.3% 68.8%   
Fast-RCNN (VGG16)70.0%68.8%68.4% 19.7%(@[0.5-0.95]), 35.9%(@0.5) 
MR-CNN78.2% 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) 
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
ION79.2% 76.4%   
CRAFT75.7% 71.3%48.5%  
OHEM78.9% 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 train83.6% 82.0% 31.5%(@[0.5-0.95]), 53.2%(@0.5) 
PVANet 9.089.8% 84.2%  750ms(CPU), 46ms(TitianX)

 

 


Leaderboard

Detection Results: VOC2012

 

 

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

 

 

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

 

 

 

 

 

NoC

Object Detection Networks on Convolutional Feature Maps

Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction

 

 

 

 

Fast R-CNN

Fast R-CNN

 

 

 

 

DeepBox

DeepBox: Learning Objectness with Convolutional Networks

 

 

 

 

MR-CNN

Object detection via a multi-region & semantic segmentation-aware CNN model

 

 

 

 

Faster R-CNN

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

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

 

 

 

 

 

 

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

R-CNN minus R

 

 

AttentionNet

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

 

 

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

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

HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection

 

 

MultiPathNet

A MultiPath Network for Object Detection

 

 

CRAFT

CRAFT Objects from Images

 

 

OHEM

Training Region-based Object Detectors with Online Hard Example Mining

Track and Transfer: Watching Videos to Simulate Strong Human Supervision for Weakly-Supervised Object Detection

Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers

 

 

 

 

 

R-FCN

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Weakly supervised object detection using pseudo-strong labels

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

 

 

 

GBD-Net

Gated Bi-directional CNN for Object Detection

Crafting GBD-Net for Object Detection

 

 

 

 

 

 

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

 

 

 

YOLOv2

YOLO9000: Better, Faster, Stronger

Yolo_mark: GUI for marking bounded boxes of objects in images for training Yolo v2

 

 

 

 

DSSD

DSSD : Deconvolutional Single Shot Detector

Wide-Residual-Inception Networks for Real-time Object Detection

Attentional Network for Visual Object Detection

 

CC-Net

Learning Chained Deep Features and Classifiers for Cascade in Object Detection

DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling

https://arxiv.org/abs/1703.10295

A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection

Discriminative Bimodal Networks for Visual Localization and Detection with Natural Language Queries

Spatial Memory for Context Reasoning in Object Detection

Improving Object Detection With One Line of Code

Accurate Single Stage Detector Using Recurrent Rolling Convolution

Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection

https://arxiv.org/abs/1704.05775

 

 

 

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

 

 

T-CNN

T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos

Object Detection from Video Tubelets with Convolutional Neural Networks

Object Detection in Videos with Tubelets and Multi-context Cues

Context Matters: Refining Object Detection in Video with Recurrent Neural Networks

CNN Based Object Detection in Large Video Images

Object Detection in Videos with Tubelet Proposal Networks

Flow-Guided Feature Aggregation for Video Object Detection

Video Object Detection using Faster R-CNN

 

 

Object Detection in 3D

Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks

  • 0
    点赞
  • 3
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
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
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