机器学习、深度学习资源汇总


(Masquerade) #1

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。

机器学习领域相关的大牛推荐

相关的理论、书籍、论文、课程、博客:

  • [Book] Yoshua Bengio, Ian Goodfellow, Aaron Courville. Deep Learning. 2015.
  • [Book] Michael Nielsen. Neural Networks and Deep Learning. 2015.
  • [Course] Convolutional Neural Networks for Visual Recognition. 2015
  • [Course] Deep Learning for Natural Language Processing. 2015.
  • [Blog] Hacker’s Guide to Neural Networks.
  • [Book] Notes on Convolutional Neural Networks
  • [Book] A guide to convolution arithmetic for deep learning

相关的库、工具

  • Theano (Python)
  • Libraries based on Theano: Lasagne, Keras, Pylearn2
  • Caffe (C++, with Python wrapper)
  • TensorFlow (Python, C++)
  • Torch (Lua)
  • ConvNetJS (Javascript)
  • Deeplearning4j (Java)
  • MatConvNet (Matlab)
  • Spark machine learning library(Java,scala,python)
  • LIBSVM A Library for Support Vector Machines(C/C++,Java and other languages)

相关的开源项目、demo

  • Facial Keypoint Detection
  • Deep Dream
  • Eyescream
  • Deep Q-network (Atari game player)
  • Caffe to Theano Model Conversion (use Caffe pretrained model in Lasagne)
  • R-CNN
  • Fast R-CNN

Leaderboard

Detection Results: VOC2012

Papers

Deep Neural Networks for Object Detection

R-CNN

Rich feature hierarchies for accurate object detection and semantic segmentation

MultiBox

Scalable Object Detection using Deep Neural Networks

SPP-Net

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

DeepID-Net

DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection

NoC

Object Detection Networks on Convolutional Feature Maps

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

YOLO

You Only Look Once: Unified, Real-Time Object Detection

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

G-CNN

G-CNN: an Iterative Grid Based Object Detector

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

R-FCN

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

MS-CNN

A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection

intro: ECCV 2016
intro: 640×480: 15 fps, 960×720: 8 fps
arxiv: http://arxiv.org/abs/1607.07155
github: https://github.com/zhaoweicai/mscnn
poster: http://www.eccv2016.org/files/posters/P-2B-38.pdf
Multi-stage Object Detection with Group Recursive Learning

intro: VOC2007: 78.6%, VOC2012: 74.9%
arxiv: http://arxiv.org/abs/1608.05159
Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection

intro: WACV 2017. SubCNN
arxiv: http://arxiv.org/abs/1604.04693
github: https://github.com/yuxng/SubCNN

PVANET

PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection

GBD-Net

Gated Bi-directional CNN for Object Detection

StuffNet

StuffNet: Using ‘Stuff’ to Improve Object Detection

Feature Pyramid Network (FPN)

Feature Pyramid Networks for Object Detection

YOLOv2

YOLO9000: Better, Faster, Stronger

DSSD

DSSD : Deconvolutional Single Shot Detector

CC-Net

Learning Chained Deep Features and Classifiers for Cascade in Object Detection

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

Detection From Video

Learning Object Class Detectors from Weakly Annotated Video

T-CNN

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

Object Detection in 3D

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