【今日CS 視覺論文速覽】 24 Jan 2019

今日CS.CV計算機視覺論文速覽

Thu, 24 Jan 2019

Totally 29 papers

Interesting:

• ExtremeNet,通過檢測物體的四個位置極值點（(top-most, leftmost,bottom-most, right-most）和中心點的位置來實作目标檢測，将目标檢測問題轉換為了一個普通的關鍵點估計問題。基于關鍵點估計，通過熱力圖峰值來尋找關鍵點并根據四個極值估計中心位置(門檻值法)。

  實作了bounding box AP of 43.2% on COCO，34.6% Mask AP（from 德克薩斯奧斯丁大學）

  

  流程如下，對每一類對象利用五個關鍵點熱力圖的幾何關系來确定bbox：

  

  得到熱力圖的網絡結構：

  

  一些相關算法：

  

  得到的結果：

  

  

  代碼：https://github.com/xingyizhou/ExtremeNet
• DeepFahion2, 用于人物服飾檢測、位姿估計、分割和重識别的基準資料集。包含了801k标注資料集和873k商家-客戶照片對。(from 香港中文 商湯)

  

  資料集包含了不同尺度、遮擋、縮放、視角下拍攝的服飾關鍵點和語義分割标注：

  

  相關資料集：

  

  文中提出了MatchCNN算法來對資料集進行評測：

  

  資料集：https://github.com/switchablenorms/DeepFashion2

• 基于壓縮感覺和全局方差最小化去除顯微鏡中的人為痕迹,擷取更清晰圖像。(from 密歇根大學)

  首先在傅裡葉空間中去除，一部分定向噪聲的頻譜，随後利用全局方差最小來補全頻譜中缺失的“锲子”部分，提高了原子力顯微鏡等顯微圖像的成像品質。

  

  

• ORSIm Detector,結合高光譜資訊的光學遙感目标檢測，內建了多通道特征抽取、學習，快速圖像金字塔比對和推舉政策，結合了頻域和空間通道特征建構的旋轉不變特征來進行學習。(from 北理工)

  

  一些檢測結果：

  

  資料集：TAS aerial car detection dataset, NWPU VHR-10 dataset2,NWPU VHR-airplane dataset ?404

  TAS >http://ai.stanford.edu/~gaheitz/Research/TAS/

• 深度學習用于地理岩相分析(Facies Classification)的資料集, （from佐治亞理工）

  

  資料集位址：https://github.com/olivesgatech/facies_classification_benchmark

Daily Computer Vision Papers

[1] Title: Bottom-up Object Detection by Grouping Extreme and Center Points

Authors:Xingyi Zhou, Jiacheng Zhuo, Philipp Krähenbühl

[2] Title: Removing Stripes, Scratches, and Curtaining with Non-Recoverable Compressed Sensing

Authors:Jonathan Schwartz, Yi Jiang, Yongjie Wang, Anthony Aiello, Pallab Bhattacharya, Hui Yuan, Zetian Mi, Nabil Bassim, Robert Hovden

[3] Title: DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images

Authors:Yuying Ge, Ruimao Zhang, Lingyun Wu, Xiaogang Wang, Xiaoou Tang, Ping Luo

[4] Title: U2-Net: A Bayesian U-Net model with epistemic uncertainty feedback for photoreceptor layer segmentation in pathological OCT scans

Authors:José Ignacio Orlando, Philipp Seeböck, Hrvoje Bogunović, Sophie Klimscha, Christoph Grechenig, Sebastian Waldstein, Bianca S. Gerendas, Ursula Schmidt-Erfurth

[5] Title: ORSIm Detector: A Novel Object Detection Framework in Optical Remote Sensing Imagery Using Spatial-Frequency Channel Features

Authors:Xin Wu, Danfeng Hong, Jiaojiao Tian, Jocelyn Chanussot, Wei Li, Ran Tao

[6] Title: Evolving the pulmonary nodules diagnosis from classical approaches to deep learning aided decision support: three decades development course and future prospect

Authors:Bo Liu, Wenhao Chi, Xinran Li, Peng Li, Wenhua Liang, Haiping Liu, Wei Wang, Jianxing He

[7] Title: Computer Vision and Metrics Learning for Hypothesis Testing: An Application of Q-Q Plot for Normality Test

Authors:Ke-Wei Huang, Mengke Qiao, Xuanqi Liu, Mingxi Dai, Siyuan Liu

[8] Title: AADS: Augmented Autonomous Driving Simulation using Data-driven Algorithms

Authors:Wei Li, Chengwei Pan, Rong Zhang, Jiaping Ren, Yuexin Ma, Jin Fang, Feilong Yan, Qichuan Geng, Xinyu Huang, Huajun Gong, Weiwei Xu, Guoping Wang, Dinesh Manocha, Ruigang Yang

[9] Title: Toward Joint Image Generation and Compression using Generative Adversarial Networks

Authors:Byeongkeun Kang, Subarna Tripathi, Truong Q. Nguyen

[10] Title: Random Forest with Learned Representations for Semantic Segmentation

Authors:Byeongkeun Kang, Truong Q. Nguyen

[11] Title: Towards Compact ConvNets via Structure-Sparsity Regularized Filter Pruning

Authors:Shaohui Lin, Rongrong Ji, Yuchao Li, Cheng Deng, Xuelong Li

[12] Title: A Boost in Revealing Subtle Facial Expressions: A Consolidated Eulerian Framework

Authors:Wei Peng, Xiaopeng Hong, Yingyue Xu, Guoying Zhao

[13] Title: Robust Learning at Noisy Labeled Medical Images:Applied to Skin Lesion Classification

Authors:Cheng Xue, Qi Dou, Xueying Shi, Hao Chen, Pheng Ann Heng

[14] Title: ODN: Opening the Deep Network for Open-set Action Recognition

Authors:Yu Shu, Yemin Shi, Yaowei Wang, Yixiong Zou, Qingsheng Yuan, Yonghong Tian

[15] Title: Deep learning Inversion of Seismic Data

Authors:Shucai Li, Bin Liu, Yuxiao Ren, Yangkang Chen, Senlin Yang, Yunhai Wang, Peng Jiang

[16] Title: Joint group and residual sparse coding for image compressive sensing

Authors:Lizhao Li, Song Xiao

[17] Title: Max-margin Class Imbalanced Learning with Gaussian Affinity

Authors:Munawar Hayat, Salman Khan, Waqas Zamir, Jianbing Shen, Ling Shao

[18] Title: Exploring Uncertainty in Conditional Multi-Modal Retrieval Systems

Authors:Ahmed Taha, Yi-Ting Chen, Xitong Yang, Teruhisa Misu, Larry Davis

[19] Title: Simultaneous Subspace Clustering and Cluster Number Estimating based on Triplet Relationship

Authors:Jie Liang, Jufeng Yang, Ming-Ming Cheng, Paul L. Rosin, Liang Wang

[20] Title: Class Activation Map Generation by Representative Class Selection and Multi-Layer Feature Fusion

Authors:Fanman Meng, Kaixu Huang, Hongliang Li, Qingbo Wu

[21] Title: A Top-down Approach to Articulated Human Pose Estimation and Tracking

Authors:Guanghan Ning, Ping Liu, Xiaochuan Fan, Chi Zhang

[22] Title: Modeling Human Motion with Quaternion-based Neural Networks

Authors:Dario Pavllo, Christoph Feichtenhofer, Michael Auli, David Grangier

[23] Title: Striking the Right Balance with Uncertainty

Authors:Salman Khan, Munawar Hayat, Waqas Zamir, Jianbing Shen, Ling Shao

[24] Title: “Is this an example image?” – Predicting the Relative Abstractness Level of Image and Text

Authors:Christian Otto, Sebastian Holzki, Ralph Ewerth

[25] Title: Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff

Authors:Yochai Blau, Tomer Michaeli

[26] Title: Programmable Neural Network Trojan for Pre-Trained Feature Extractor

Authors:Yu Ji, Zixin Liu, Xing Hu, Peiqi Wang, Youhui Zhang

[27] Title: A Machine Learning Benchmark for Facies Classification

Authors:Yazeed Alaudah, Patrycja Michalowicz, Motaz Alfarraj, Ghassan AlRegib

[28] Title: Understanding Geometry of Encoder-Decoder CNNs

Authors:Jong Chul Ye, Woon Kyoung Sung

[29] Title: Aggregated Pairwise Classification of Statistical Shapes

Authors:Min Ho Cho, Sebastian Kurtek, Steven N. MacEachern

Papers from arxiv.org

更多精彩請移步首頁

pic from pixels.com