GitHub：目標檢測最全論文集錦

導言

目標檢測（Object Detection）能夠識別一幅圖像中的多個物體，定位不一樣物體的同時（邊界框），貼上相應的類別。簡單來講，解決了what和where問題。授人以魚，不如授人以漁，本文不會具體介紹某類/某種算法（one-stage or two-stage），但會給出目標檢測相關論文的最強合集（持續更新ing）。爲了follow潮流（裝B），Amusi將目標檢測論文合集的github庫起名爲awesome-object-detection。

CVer

編輯: Amusi

校稿: Amusi

Object Detection Wiki

Object detection is a computer technology related to computer vision and image processing that deals with detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and videos. Well-researched domains of object detection include face detection and pedestrian detection. Object detection has applications in many areas of computer vision, including image retrieval and video surveillance.
Object Detection

首先，Amusi先安利一個網站，打開下述連接後，既能夠看到使人熱血沸騰的畫面。

link:

https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html

當初看到這個網址，我很驚訝，連接上寫的是2015/10/09，我覺得是很老的資源，但看到內容後，着實震驚了。該庫在handong大神的我的主頁上，但並無Object Detection單獨的github庫。受此啓發，我擅自（由於尚未獲得本人贊成）將handong大神的Object Detection整理的內容進行精簡和補充（實在班門弄斧了）。因而建立了一個名爲awesome-object-detection的github庫。

Awesome-Object-Detection

接下來，重點介紹一下這個「很copy」的庫。awesome-object-detection的目的是爲了提供一個目標檢測（Object Detection）學習的平臺。特色是：介紹最新的paper和最新的code（儘可能更新！）因爲Amusi仍是初學者，目前尚未辦法對每一個paper進行介紹，但後續會推出paper精講的內容，也歡迎你們star，fork並pull本身所關注到最新object detection的工做。

那來看看目前，awesome-object-detection裏有哪些乾貨吧~

爲了節省篇幅，這裏只介紹較爲重要的工做：

R-CNN三件套（R-CNN Fast R-CNN和Faster R-CNN）

Light-Head R-CNN

Cascade R-CNN

YOLO三件套（YOLOv1 YOLOv2 YOLOv3）

SSD（SSD DSSD FSSD ESSD Pelee）

R-FCN

FPN

DSOD

RetinaNet

DetNet

...

你們對常見的R-CNN系列和YOLO系列必定很熟悉了，這裏Amusi也不想重複，由於顯得沒有逼格~這裏主要簡單推薦兩篇paper，來凸顯一下awesome-object-detection的意義。

Pelee

《Pelee: A Real-Time Object Detection System on Mobile Devices》
intro: (ICLR 2018 workshop track)

arxiv: https://arxiv.org/abs/1804.06882

github: https://github.com/Robert-JunWang/Pelee

Abstract：An increasing need of running Convolutional Neural Network (CNN) models on mobile devices with limited computing power and memory resource encourages studies on efficient model design. A number of efficient architectures have been proposed in recent years, for example, MobileNet, ShuffleNet, and NASNet-A. However, all these models are heavily dependent on depthwise separable convolution which lacks efficient implementation in most deep learning frameworks. In this study, we propose an efficient architecture named PeleeNet, which is built with conventional convolution instead. On ImageNet ILSVRC 2012 dataset, our proposed PeleeNet achieves a higher accuracy by 0.6% (71.3% vs. 70.7%) and 11% lower computational cost than MobileNet, the state-of-the-art efficient architecture. Meanwhile, PeleeNet is only 66% of the model size of MobileNet. We then propose a real-time object detection system by combining PeleeNet with Single Shot MultiBox Detector (SSD) method and optimizing the architecture for fast speed. Our proposed detection system, named Pelee, achieves 76.4% mAP (mean average precision) on PASCAL VOC2007 and 22.4 mAP on MS COCO dataset at the speed of 17.1 FPS on iPhone 6s and 23.6 FPS on iPhone 8. The result on COCO outperforms YOLOv2 in consideration of a higher precision, 13.6 times lower computational cost and 11.3 times smaller model size. The code and models are open sourced.

Quantization Mimic

《Quantization Mimic: Towards Very Tiny CNN for Object Detection》

Tsinghua University1 & The Chinese University of Hong Kong2 &SenseTime3

arxiv: https://arxiv.org/abs/1805.02152

注：看一下這篇paper聯名的機構......2018-05-06發佈在arXiv（熱乎乎的還燙手）

Abstract：In this paper, we propose a simple and general framework for training very tiny CNNs for object detection. Due to limited representation ability, it is challenging to train very tiny networks for complicated tasks like detection. To the best of our knowledge, our method, called Quantization Mimic, is the first one focusing on very tiny networks. We utilize two types of acceleration methods: mimic and quantization. Mimic improves the performance of a student network by transfering knowledge from a teacher network. Quantization converts a full-precision network to a quantized one without large degradation of performance. If the teacher network is quantized, the search scope of the student network will be smaller. Using this property of quantization, we propose Quantization Mimic. It first quantizes the large network, then mimic a quantized small network. We suggest the operation of quantization can help student network to match the feature maps from teacher network. To evaluate the generalization of our hypothesis, we carry out experiments on various popular CNNs including VGG and Resnet, as well as different detection frameworks including Faster R-CNN and R-FCN. Experiments on Pascal VOC and WIDER FACE verify our Quantization Mimic algorithm can be applied on various settings and outperforms state-of-the-art model acceleration methods given limited computing resouces.

總結

awesome-object-detection這個庫的目的是爲了儘量介紹最新的關於目標檢測（Object Detection）相關的工做（paper and code）。因爲Amusi仍是初學者，因此整理很差/不規範的地方，還請你們及時指出。由於該庫直接copy了handong大神的內容，因此若是有版權侵犯，我會當即刪除/修改（正在聯繫handong大神ing）。

若是你們以爲awesome-object-detection對本身有一丟丟幫助，那麼歡迎你們star和fork，哈哈，更歡迎你們pull~

打開「閱讀原文」，能夠直接訪問awesome-object-detection

link：https://github.com/amusi/awesome-object-detection