【今日CV 计算机视觉论文速览】Mon, 4 Mar 2019
今日CS.CV计算机视觉论文速览
Mon, 4 Mar 2019
Totally 39 papers
Interesting:
📚MaskScoring R-CNN 为实例分割任务中增加了预测质量的评分结果,文章提出了网络模块学习预测实例的质量，并为实例分割结果进行打分。这一模块通过实例特征和对应的预测掩膜联合起来得到掩膜区域，实验表明这一机制提高了实例分割的结果，并显著增强了多个的性能。（from 华中科技大学）
实验显示MaskIoU与分数具有更强的相关性：
网络中输出maskIoU的区域及其不同设计：
代码：https://github.com/zjhuang22/maskscoring_rcnn.
ref 公众号
📚 EvoNet基于多图像的超分辨网络，利用基于残差的EvoNet输出多张超分辨重建图像(2X)，并基于图像进行shift-and-fusion融合(2x)，最终利用Evo成像模型得到最终的超分辨结果。（from Poland and with Silesian University of Technology）
一些结果：
一些相关算法比较：
高精度数据集DIV 2K
📚
视频中非标记目标的探索，面临着定位和多重物体的挑战。此外现实中的物体还具有明显的长尾效应。研究人员利用10+个小时的视频数据中抽取了360,000个目标，并基于双目多帧候选区域、通用目标追踪、非标记数据识别及其聚类来完成未知类别的探索。(from 亚琛工业大学)
论文的流程如下：
实际中的表现如下：
下图可以看到数据具有明显的长尾效应：
一些相关算法的表现：
相关数据集：KATTI Raw, OXFORD ROBOTCAR DATASET
作者的项目网站：https://www.vision.rwth-aachen.de/page/lsom
📚
提出了一种基于Wasserstein GAN的模型用于图像去雾,在无需多张图像或者先验的情况下，利用GAN在Wasserstein 损失的基础上学习干净图像的概率分布，并基于梯度惩罚实现Lipschitz约束。再结合L1和纹理损失后，最终得到了端到端的单图像去噪模型。（from Indian Institute of Technology Kharagpur）
模型损失定义如下：
自然条件下去雾结果：
人工数据下去雾结果：
相关方法和结果：
😎 相关数据集O-Haze,D-Hazy, ref。
emoji
📚
📚
📚
📚
Daily Computer Vision Papers
[1] Title: A Behavioral Approach to Visual Navigation with Graph Localization Networks
Authors:Kevin Chen, Juan Pablo de Vicente, Gabriel Sepulveda, Fei Xia, Alvaro Soto, Marynel Vazquez, Silvio Savarese
[2] ***Title: Deep Learning for Multiple-Image Super-Resolution
Authors:Michal Kawulok, Pawel Benecki, Szymon Piechaczek, Krzysztof Hrynczenko, Daniel Kostrzewa, Jakub Nalepa
[3] Title: Quantifying contribution and propagation of error from computational steps, algorithms and hyperparameter choices in image classification pipelines
Authors:Aritra Chowdhury, Malik Magdon-Ismail, Bulent Yener
[4] **Title: Single Image Haze Removal Using Conditional Wasserstein Generative Adversarial Networks
Authors:Joshua Peter Ebenezer, Bijaylaxmi Das, Sudipta Mukhopadhyay
[5] Title: Deep Neural Network and Data Augmentation Methodology for off-axis iris segmentation in wearable headsets
Authors:Viktor Varkarakis, Shabab Bazrafkan, Peter Corcoran
[6] Title: Automatic microscopic cell counting by use of unsupervised adversarial domain adaptation and supervised density regression
Authors:Shenghua He, Kyaw Thu Minn, Lilianna Solnica-Krezel, Hua Li, Mark Anastasio
[7] Title: Answer Them All! Toward Universal Visual Question Answering Models
Authors:Robik Shrestha, Kushal Kafle, Christopher Kanan
[8] *Title: Large-Scale Object Mining for Object Discovery from Unlabeled Video
Authors:Aljosa Osep, Paul Voigtlaender, Jonathon Luiten, Stefan Breuers, Bastian Leibe
[9] Title: Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentation
Authors:Xiaomeng Li, Lequan Yu, Hao Chen, Chi-Wing Fu, Pheng-Ann Heng
[10] **Title: Octree guided CNN with Spherical Kernels for 3D Point Clouds
Authors:Huan Lei, Naveed Akhtar, Ajmal Mian
[11] Title: Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos
Authors:Bo Hu, Jianfei Cai, Tat-Jen Cham, Junsong Yuan
[12] Title: Provably scale-covariant networks from oriented quasi quadrature measures in cascade
Authors:Tony Lindeberg
[13] ***Title: Adversarial Generation of Handwritten Text Images Conditioned on Sequences
Authors:Eloi Alonso, Bastien Moysset, Ronaldo Messina
[14] Title: Frequency Domain Transformer Networks for Video Prediction
Authors:Hafez Farazi, Sven Behnke
[15] Title: Object Recognition in Deep Convolutional Neural Networks is Fundamentally Different to That in Humans
Authors:Ben Lonnqvist, Alasdair D. F. Clarke, Ramakrishna Chakravarthi
[16] **Title: Mask Scoring R-CNN
Authors:Zhaojin Huang, Lichao Huang, Yongchao Gong, Chang Huang, Xinggang Wang
[17] **Title: Single Image Deblurring and Camera Motion Estimation with Depth Map
Authors:Liyuan Pan, Yuchao Dai, Miaomiao Liu
[18] Title: Lung CT Imaging Sign Classification through Deep Learning on Small Data
Authors:Guocai He
[19] *Title: Pyramid Feature Selective Network for Saliency detection
Authors:Ting Zhao, Xiangqian Wu
[20] *Title: Image-Based Geo-Localization Using Satellite Imagery
Authors:Sixing Hu, Gim Hee Lee
[21] Title: Video Extrapolation with an Invertible Linear Embedding
Authors:Robert Pottorff, Jared Nielsen, David Wingate
[22] Title: Local Geometric Indexing of High Resolution Data for Facial Reconstruction from Sparse Markers
Authors:Matthew Cong, Lana Lan, Ronald Fedkiw
[23] ***Title: A Sketch Based 3D Shape Retrieval Approach Based on Efficient Deep Point-to-Subspace Metric Learning
Authors:Yinjie Lei, Ziqin Zhou, Pingping Zhang, Yulan Guo, Zijun Ma, Lingqiao Liu
[24] **Title: Self-supervised Learning for Single View Depth and Surface Normal Estimation
Authors:Huangying Zhan, Chamara Saroj Weerasekera, Ravi Garg, Ian Reid
[25] Title: Video Summarization via Actionness Ranking
Authors:Mohamed Elfeki, Ali Borji
[26] *Title: GAN Based Image Deblurring Using Dark Channel Prior
Authors:Shuang Zhang, Ada Zhen, Robert L. Stevenson
[27] Title: Appearance-based Gesture recognition in the compressed domain
Authors:Shaojie Xu, Anvesha Amaravati, Justin Romberg, Arijit Raychowdhury
[28] Title: Broad Neural Network for Change Detection in Aerial Images
Authors:Shailesh Shrivastava, Alakh Aggarwal, Pratik Chattopadhyay
[29] Title: On the Effectiveness of Low Frequency Perturbations
Authors:Yash Sharma, Gavin Weiguang Ding, Marcus Brubaker
[30] *Title: SPDA: Superpixel-based Data Augmentation for Biomedical Image Segmentation
Authors:Yizhe Zhang, Lin Yang, Hao Zheng, Peixian Liang, Colleen Mangold, Raquel G. Loreto, David P. Hughes, Danny Z. Chen
[31] Title: A Deep DUAL-PATH Network for Improved Mammogram Image Processing
Authors:Heyi Li, Dongdong Chen, William H. Nailon, Mike E. Davies, Dave Laurenson
[32] Title: Multi-Object Representation Learning with Iterative Variational Inference
Authors:Klaus Greff, Raphaël Lopez Kaufmann, Rishab Kabra, Nick Watters, Chris Burgess, Daniel Zoran, Loic Matthey, Matthew Botvinick, Alexander Lerchner
[33] *Title: Learning To Follow Directions in Street View
Authors:Karl Moritz Hermann, Mateusz Malinowski, Piotr Mirowski, Andras Banki-Horvath, Keith Anderson, Raia Hadsell
[34] *Title: TamperNN: Efficient Tampering Detection of Deployed Neural Nets
Authors:Erwan Le Merrer, Gilles Trédan
[35] Title: Optimal Projection Guided Transfer Hashing for Image Retrieval
Authors:Ji Liu, Lei Zhang
[36] *Title: A Unified Neural Architecture for Instrumental Audio Tasks
Authors:Steven Spratley, Daniel Beck, Trevor Cohn
[37] Title: A detailed comparative study of open source deep learning frameworks
Authors:Ghadeer Al-Bdour, Raffi Al-Qurran, Mahmoud Al-Ayyoub, Ali Shatnawi
[38] Title: Neuromodulated Goal-Driven Perception in Uncertain Domains
Authors:Xinyun Zou, Soheil Kolouri, Praveen K. Pilly, Jeffrey L. Krichmar
[39] *Title: Speeding up Deep Learning with Transient Servers
Authors:Shijian Li, Robert J. Walls, Lijie Xu, Tian Guo
pic from pixels.com
😢writing_hand:致歉：上周学校事情很忙😵，没有及时更新！感谢小伙伴们一直关注，会坚持update~~❤
