# 前言 本书是作者在学习和使用深度学习过程中总结的博客性质的文章。 日前深度学习可以说是计算机界最火的一个应用领域了，在OCR，ASR，NLP上均取得了突破性的进展。密切关注深度学习领域的紧张可以说是深度学习工作者必不可少的工作内容之一了。这本书写作的目的在于对深度学习领域中最前沿的技术，源码以及论文的分析总结。本书很少涉及基础知识的介绍，主要内容在于跟踪深度学习中比较流行的，效果比较好的，创新性高的，对应用有质的提升的论文及源码，并结合实际经验进行分析总结。 当然，由于能力和经验都有限，难免会有分析错误的地方，欢迎在评论区给与指出。 本书将会长期更新下去，各种版本的电子书均可以在[gitbook](https://legacy.gitbook.com/book/senliuy/computer-vision/details)主页下载。如果有想看的论文，可以在评论区留言。如果觉得对您有帮助，欢迎在主页加星，你的星将是我更新下去最大的动力。 更新日志： * 2018-01-12：Rich feature hierarchies for accurate object detection and semantic segmentation * 2018-01-25：spatial pyramid pooling in deep convolutional networks for visual recognition * 2018-01-31：Fast R-CNN * 2018-02-06：faster r-cnn towards real-time object detection with region proposal networks * 2018-02-12：detecting text in natural image with connectionist text proposal network * 2018-03-16：Connectionist Temporal Classification : Labelling Unsegmented Sequence Data with Recurrent Neural Networks * 2018-03-22：Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation * 2018-03-22：Neural Machine Translation by Jointly Learning to Align and Translate * 2018-05-07：About Long Short Term Memory * 2018-05-09：Speech Recognition with Deep Recurrent Neural Network * 2018-05-30：ImageNet Classification with Deep Convolutional Neural Network * 2018-05-31：Very Deep Convolutional NetWorks for Large-Scale Image Recognition * 2018-06-05：Going Deeper with Convolutions * 2018-06-05：Deep Residual Learning for Image Recognition * 2018-06-08：Densely Connected Convolutional Networks * 2018-06-15：R-FCN: Object Detection via Region-based Fully Convolutuional Networks * 2018-07-01：Mask R-CNN * 2018-07-04：字符验证码破解 * 2018-07-10：You Only Look Once: Unified, Real-Time Object Detection * 2018-07-19：SSD: Single Shot MultiBox Detector * 2018-07-25：YOLO9000：Better, Faster, Stronger * 2018-07-27：YOLOv3：An Incremental Improvement * 2018-08-01：Learning to Segment Every Thing * 2018-08-06：Reading Text in the Wild with Convolutional Neural Networks * 2018-08-09：Spatial Transform Networks * 2018-08-10：Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework * 2018-08-14：Robust Scene Text Recognition with Automatic Rectification * 2018-08-20：DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images * 2018-08-28：Holistically-Nested Edge Detection * 2018-08-29：Scene Text Detection via Holistic, Multi-Channel Prediction * 2018-09-04：U-Net: Convolutional Networks for Biomedical Image Segmentation * 2018-09-06：DenseBox: Unifying Landmark Localization with End to End Object Detection * 2018-09-06：UnitBox: An Advanced Object Detection Network * 2018-09-27：Arbitrary-Oriented Scene Text Detection via Rotation Proposals * 2018-10-15：SNIPER: Efficient Multi-Scale Training * 2018-10-23：Squeeze-and-Excitation Networks * 2018-11-04：Attention Is All You Need * 2018-11-05：BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding * 2018-11-08：Focal Loss for Dense Object Detection * 2018-11-12：SQUEEZENET: ALEXNET-LEVEL ACCURACY WITH 50X FEWER PARAMETERS AND < 0.5MB MODEL SIZE * 2018-11-16：MobileNet v1 and MobileNet v2 * 2018-11-26：Xception: Deep Learning with Depthwise Separable Convolutions * 2018-11-28：Aggregated Residual Transformations for Deep Neural Networks * 2018-12-04：ShuffNet v1 and ShuffleNet v2 * 2018-12-10：CondenseNet: An Efficient DenseNet using Learned Group Convolutions * 2018-12-11：PolyNet: A Pursuit of Structural Diversity in Very Deep Networks * 2018-12-15：Neural Architecture Search with Reinforecement Learning * 2018-12-17：Learning Transferable Architectures for Scalable Image Recognition * 2018-12-19：Progressive Neural Architecture Search * 2018-12-26：实例解析：12306验证码破解 * 2019-01-06：Batch Normalization * 2019-01-10：Layer Normalization * 2019-01-17：Weight Normalization * 2019-01-28：Recurrent Neural Network based Language Model * 2019-01-29：Image Style Transfer Using Convolutional Nerual Networks * 2019-02-12：Instance Normalization * 2019-02-13：Group Normalization * 2019-02-19：Hierarchical Attention Networks for Document Classification * 2019-02-23：Regularized Evolution for Image Classifier Architecture Search * 2019-02-27：Switchable Normalization * 2019-11-17：Show and Tell: A Neural Image Caption Generator * 2020-02-15：PixelLink: Detecting Scene Text via Instance Segmentation * 2020-02-24：Bidirectional Scene Text Recognition with a Single Decoder * 2020-06-14：Background Matting： The World is Your Green Screen --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://senliuy.gitbook.io/advanced-deep-learning/master.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.