【今日CS 視覺論文速覽】 21 Jan 2019

今日CS.CV計算機視覺論文速覽

Mon, 21 Jan 2019

Totally 23 papers

Interesting:

• 用于手寫字型超分辨的生成對抗分類器，通過在GAN後增加額外的分類器，可以有效提升超分辨率。(from 西交利物浦)

  

  引入的分類器相關損失:

  

  生成器、判别器和分類器的内部架構：

  

  資料集:

  CASIA,MNIST

  RELATED:https://github.com/integeruser/CASIA-HWDB1.1-cnn

• 基于塊比對的圖像去噪,基于GMM聚類的方法提出新的詳細圖像塊比對方法，克服BM3D, LPCA and PLOW存在的問題。(from 波特蘭大學)

  

  資料集： Berkeley Segmentation Dataset

• DeepOtsu，基于堆疊深度學習的手寫/印刷品檔案圖像品質提升，随後二值化的過程。（from 格尼羅根大學 荷蘭）

  文章中提出的退化模型，包含了目标和噪聲兩部分：

  

  

  用不同的cnn堆疊優化方法：

  

  一些結果：

  

  相關資料集：

  Train：

  DIBCO 2009 [43], H-DIBCO 2010 [44] and H-DIBCO 2012 [45]， Bickely-diary dataset [46], PHIDB [47] and the Synchromedia Multispectral dataset [48].

  Test：

  DIBCO 2011 [49],DIBCO 2013 [50], H-DIBCO 2014 [51] and H-DIBCO 2016 [52]

  DIBCO2017 《–DIBCO資料集

• 快速高維濾波核,基于Nystrom method将大型矩陣特征值分解進行約化，并應用于雙邊濾波和非線性均值濾波中。

  實作的去噪結果：

  

  高速高品質：

  

• 尺度注意力的人群計數網絡，多層級的密度圖估計，引入尺度損失函數解決了距離相機遠近的尺度問題、不同分辨率下的尺度問題。(from亞馬遜)

  

  資料集： UCF-QNRF, ShanghaiTechA & B and UCF_CC_50.
• 基于條件GANs生成血紅細胞實作圖像增強,基于image-to-image 遷移技術通過給定細胞的mask來生成逼真的細胞圖像(from 南韓Noul公司 )

  

• 深度學習的總結

Daily Computer Vision Papers

[1] Title: ULDor: A Universal Lesion Detector for CT Scans with Pseudo Masks and Hard Negative Example Mining

Authors:Youbao Tang, Ke Yan, Yuxing Tang, Jiamin Liu, Jing Xiao, Ronald M. Summers

[2] Title: Embedded CNN based vehicle classification and counting in non-laned road traffic

Authors:Mayank Singh Chauhan, Arshdeep Singh, Mansi Khemka, Arneish Prateek, Rijurekha Sen

[3] Title: Adapting Convolutional Neural Networks for Geographical Domain Shift

Authors:Pavel Ostyakov, Sergey I. Nikolenko

[4] Title: Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection

Authors:Fan Yang, Lei Zhang, Sijia Yu, Danil Prokhorov, Xue Mei, Haibin Ling

[5] Title: Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translation

Authors:Wei Sun, Tianfu Wu

[6] Title: Red blood cell image generation for data augmentation using Conditional Generative Adversarial Networks

Authors:Oleksandr Bailo, DongShik Ham, Young Min Shin

[7] Title: Generative Adversarial Classifier for Handwriting Characters Super-Resolution

Authors:Zhuang Qian, Kaizhu Huang, Qiufeng Wang, Jimin Xiao, Rui Zhang

[8] Title: Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification

Authors:Youngmin Ro, Jongwon Choi, Dae Ung Jo, Byeongho Heo, Jongin Lim, Jin Young Choi

[9] Title: Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification

Authors:Weitao Feng, Zhihao Hu, Wei Wu, Junjie Yan, Wanli Ouyang

[10] Title: Fast High-Dimensional Kernel Filtering

Authors:Pravin Nair, Kunal N. Chaudhury

[11] Title: CRDN: Cascaded Residual Dense Networks for Dynamic MR Imaging with Edge-enhanced Loss Constraint

Authors:Ziwen Ke, Shanshan Wang, Huitao Cheng, Leslie Ying, Qiegen Liu, Hairong Zheng, Dong Liang

[12] Title: Linearized ADMM and Fast Nonlocal Denoising for Efficient Plug-and-Play Restoration

Authors:Unni V. S., Sanjay Ghosh, Kunal N. Chaudhury

[13] Title: DeepOtsu: Document Enhancement and Binarization using Iterative Deep Learning

Authors:Sheng He, Lambert Schomaker

[14] Title: Learning Mutually Local-global U-nets For High-resolution Retinal Lesion Segmentation in Fundus Images

Authors:Zizheng Yan, Xiaoguang Han, Changmiao Wang, Yuda Qiu, Zixiang Xiong, Shuguang Cui

[15] Title: Good Similar Patches for Image Denoising

Authors:Si Lu

[16] Title: High-speed Video from Asynchronous Camera Array

Authors:Si Lu

[17] Title: A Survey of the Recent Architectures of Deep Convolutional Neural Networks

Authors:Asifullah Khan, Anabia Sohail, Umme Zahoora, Aqsa Saeed Qureshi

[18] Title: Scale-Aware Attention Network for Crowd Counting

Authors:Rahul Rama Varior, Bing Shuai, Joe Tighe, Davide Modolo

[19] Title: FARSA: Fully Automated Roadway Safety Assessment

Authors:Weilian Song, Scott Workman, Armin Hadzic, Xu Zhang, Eric Green, Mei Chen, Reginald Souleyrette, Nathan Jacobs

[20] Title: Instance-Level Microtubule Segmentation Using Recurrent Attention

Authors:Samira Masoudi, Afsaneh Razi, Cameron H.G. Wright, Jay C. Gatlin, Ulas Bagci

[21] Title: PSACNN: Pulse Sequence Resilient Fast Whole Brain Segmentation

Authors:Amod Jog, Andrew Hoopes, Douglas N. Greves, Koen Van Leemput, Bruce Fischl

[22] Title: Robust Anomaly Detection in Images using Adversarial Autoencoders

Authors:Laura Beggel, Michael Pfeiffer, Bernd Bischl

[23] Title: Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data

Authors:Yinhao Zhu, Nicholas Zabaras, Phaedon-Stelios Koutsourelakis, Paris Perdikaris

Papers from arxiv.org

更多精彩請移步首頁

pic from pixels.com