出品 | 深度學習這件小事公眾號
[1] Self-Supervised Ranking for Representation Learning作者 | Ali Varamesh, Ali Diba, Tinne Tuytelaars, Luc Van Gool連結 | https://arxiv.org/abs/2010.07258 [2] Vision-Aided Radio: User Identity Match in Radio and Video Domains Using Machine Learning作者 | Vinicius M. de Pinho, Marcello L. R. de Campos, Luis Uzeda Garcia, Dalia Popescu連結 | https://arxiv.org/abs/2010.07219 備註 | Submitted to IEEE Access[3] Back to the Future: Cycle Encoding Prediction for Self-supervised Contrastive Video Representation Learning作者 | Xinyu Yang, Majid Mirmehdi, Tilo Burghardt連結 | https://arxiv.org/abs/2010.07217 [4] Manifold-Net: Using Manifold Learning for Point Cloud Classification作者 | Dinghao Yang, Wei Gao連結 | https://arxiv.org/abs/2010.07215 [5] Learning Propagation Rules for Attribution Map Generation作者 | Yiding Yang, Jiayan Qiu, Mingli Song, Dacheng Tao, Xinchao Wang連結 | https://arxiv.org/abs/2010.07210 備註 | Accepted by ECCV 2020[6] A Vector-based Representation to Enhance Head Pose Estimation作者 | Zhiwen Cao, Zongcheng Chu, Dongfang Liu, Yingjie Chen連結 | https://arxiv.org/abs/2010.07184 [7] WeightAlign: Normalizing Activations by Weight Alignment作者 | Xiangwei Shi, Yunqiang Li, Xin Liu, Jan van Gemert連結 | https://arxiv.org/abs/2010.07160 備註 | The first three authors contributed equally; accepted by ICPR 2020[8] Multi-class segmentation under severe class imbalance: A case study in roof damage assessment作者 | Jean-Baptiste Boin, Nat Roth, Jigar Doshi, Pablo Llueca, Nicolas Borensztein連結 | https://arxiv.org/abs/2010.07151 備註 | Submitted to the Artificial Intelligence for Humanitarian Assistance and Disaster Response Workshop at NeurIPS 2020[9] Online Anomaly Detection in Surveillance Videos with Asymptotic Bounds on False Alarm Rate作者 | Keval Doshi, Yasin Yilmaz連結 | https://arxiv.org/abs/2010.07110 備註 | Submitted to Pattern Recognition. arXiv admin note: substantial text overlap with arXiv:2004.07941[10] A New Distributional Ranking Loss With Uncertainty: Illustrated in Relative Depth Estimation作者 | Alican Mertan, Yusuf Huseyin Sahin, Damien Jade Duff, Gozde Unal連結 | https://arxiv.org/abs/2010.07091 備註 | Accepted at 3DV 2020[11] Better Patch Stitching for Parametric Surface Reconstruction作者 | Zhantao Deng, Jan Bednařík, Mathieu Salzmann, Pascal Fua連結 | https://arxiv.org/abs/2010.07021 備註 | Accepted to 3DV 2020[12] FC-DCNN: A densely connected neural network for stereo estimation作者 | Dominik Hirner, Friedrich Fraundorfer連結 | https://arxiv.org/abs/2010.06950 備註 | This paper has been accepted to the ICPR 2020 conference in Milan which will be held on the 10-15 January 2021. Therefore this work has not yet been presented[13] Relative Depth Estimation as a Ranking Problem作者 | Alican Mertan, Damien Jade Duff, Gozde Unal連結 | https://arxiv.org/abs/2010.06944 備註 | Accepted at SIU 2020[14] Deep Learning from Small Amount of Medical Data with Noisy Labels: A Meta-Learning Approach作者 | Görkem Algan, Ilkay Ulusoy, Şaban Gönül, Banu Turgut, Berker Bakbak連結 | https://arxiv.org/abs/2010.06939 備註 | This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible[15] PP-LinkNet: Improving Semantic Segmentation of High Resolution Satellite Imagery with Multi-stage Training作者 | An Tran, Ali Zonoozi, Jagannadan Varadarajan, Hannes Kruppa連結 | https://arxiv.org/abs/2010.06932 [16] AMPA-Net: Optimization-Inspired Attention Neural Network for Deep Compressed Sensing作者 | Nanyu Li, Charles C. Zhou連結 | https://arxiv.org/abs/2010.06907 [17] Development of Open Informal Dataset Affecting Autonomous Driving作者 | Yong-Gu Lee, Seong-Jae Lee, Sang-Jin Lee, Tae-Seung Baek, Dong-Whan Lee, Kyeong-Chan Jang, Ho-Jin Sohn, Jin-Soo Kim連結 | https://arxiv.org/abs/2010.06900 備註 | 26 pages, 16 figures[18] Adaptive-Attentive Geolocalization from few queries: a hybrid approach作者 | Gabriele Moreno Berton, Valerio Paolicelli, Carlo Masone, Barbara Caputo連結 | https://arxiv.org/abs/2010.06897 [19] Semantic Segmentation for Partially Occluded Apple Trees Based on Deep Learning作者 | Zijue Chen, David Ting, Rhys Newbury, Chao Chen連結 | https://arxiv.org/abs/2010.06879 [20] Semantic Flow-guided Motion Removal Method for Robust Mapping作者 | Xudong Lv, Boya Wang, Dong Ye, Shuo Wang連結 | https://arxiv.org/abs/2010.06876 [21] Multi-Scale Networks for 3D Human PoseEstimation with Inference Stage Optimization作者 | Cheng Yu, Bo Wang, Bo Yang, Robby T. Tan連結 | https://arxiv.org/abs/2010.06844 備註 | 14 pages, 13 figures. arXiv admin note: substantial text overlap with arXiv:2004.11822[22] Towards Optimal Filter Pruning with Balanced Performance and Pruning Speed作者 | Dong Li, Sitong Chen, Xudong Liu, Yunda Sun, Li Zhang連結 | https://arxiv.org/abs/2010.06821 [23] Ferrograph image classification作者 | Peng Peng, Jiugen Wang連結 | https://arxiv.org/abs/2010.06777 [24] Rotation Averaging with Attention Graph Neural Networks作者 | Joshua Thorpe, Ruwan Tennakoon, Alireza Bab-Hadiashar連結 | https://arxiv.org/abs/2010.06773 [25] Are all negatives created equal in contrastive instance discrimination?作者 | Tiffany (Tianhui)Cai, Jonathan Frankle, David J. Schwab, Ari S. Morcos連結 | https://arxiv.org/abs/2010.06682 [26] Intrapersonal Parameter Optimization for Offline Handwritten Signature Augmentation作者 | Teruo M. Maruyama, Luiz S. Oliveira, Alceu S. Britto Jr, Robert Sabourin連結 | https://arxiv.org/abs/2010.06663 備註 | 16 pages, 11 figures, To appear in the IEEE Transactions on Information Forensics & Security[27] Video Action Understanding: A Tutorial作者 | Matthew Hutchinson, Vijay Gadepally連結 | https://arxiv.org/abs/2010.06647 備註 | Shortened version submitted to ACM CSUR[28] On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation作者 | Raul de Queiroz Mendes, Eduardo Godinho Ribeiro, Nicolas dos Santos Rosa, Valdir Grassi Jr連結 | https://arxiv.org/abs/2010.06626 [29] A spatial model checker in GPU (extended version)作者 | Laura Bussi, Vincenzo Ciancia, Fabio Gadducci連結 | https://arxiv.org/abs/2010.07284 [30] Privacy-Preserving Object Detection & Localization Using Distributed Machine Learning: A Case Study of Infant Eyeblink Conditioning作者 | Stefan Zwaard, Henk-Jan Boele, Hani Alers, Christos Strydis, Casey Lew-Williams, Zaid Al-Ars連結 | https://arxiv.org/abs/2010.07259 備註 | This is a preprint version of "Privacy-Preserving Object Detection & Localization Using Distributed Machine Learning: A Case Study of Infant Eyeblink Conditioning". This work consists of 12 pages including refs and, 4 tables and 7 figures[31] Fader Networks for domain adaptation on fMRI: ABIDE-II study作者 | Marina Pominova, Ekaterina Kondrateva, Maxim Sharaev, Alexander Bernstein, Evgeny Burnaev連結 | https://arxiv.org/abs/2010.07233 [32] Domain Shift in Computer Vision models for MRI data analysis: An Overview作者 | Ekaterina Kondrateva, Marina Pominova, Elena Popova, Maxim Sharaev, Alexander Bernstein, Evgeny Burnaev連結 | https://arxiv.org/abs/2010.07222 [33] Data Augmentation for Meta-Learning作者 | Renkun Ni, Micah Goldblum, Amr Sharaf, Kezhi Kong, Tom Goldstein連結 | https://arxiv.org/abs/2010.07092 [34] 3D Segmentation Networks for Excessive Numbers of Classes: Distinct Bone Segmentation in Upper Bodies作者 | Eva Schnider, Antal Horváth, Georg Rauter, Azhar Zam, Magdalena Müller-Gerbl, Philippe C. Cattin連結 | https://arxiv.org/abs/2010.07045 備註 | 10 pages, 3 figures, 2 tables, accepted into MICCAI 2020 International Workshop on Machine Learning in Medical Imaging[35] Understanding bias in facial recognition technologies連結 | https://arxiv.org/abs/2010.07023 [36] Fast meningioma segmentation in T1-weighted MRI volumes using a lightweight 3D deep learning architecture作者 | David Bouget, André Pedersen, Sayied Abdol Mohieb Hosainey, Johanna Vanel, Ole Solheim, Ingerid Reinertsen連結 | https://arxiv.org/abs/2010.07002 備註 | 15 pages, 7 figures, submitted to SPIE journal of Medical Imaging[37] Using satellite imagery to understand and promote sustainable development作者 | Marshall Burke, Anne Driscoll, David B. Lobell, Stefano Ermon連結 | https://arxiv.org/abs/2010.06988 [38] Practical Deep Raw Image Denoising on Mobile Devices作者 | Yuzhi Wang, Haibin Huang, Qin Xu, Jiaming Liu, Yiqun Liu, Jue Wang連結 | https://arxiv.org/abs/2010.06935 [39] Efficient and high accuracy 3-D OCT angiography motion correction in pathology作者 | Stefan B. Ploner, Martin F. Kraus, Eric M. Moult, Lennart Husvogt, Julia Schottenhamml, A. Yasin Alibhai, Nadia K. Waheed, Jay S. Duker, James G. Fujimoto, Andreas K. Maier連結 | https://arxiv.org/abs/2010.06931 備註 | 22 pages, 11 figures, 4 tables[40] Identifying Wrongly Predicted Samples: A Method for Active Learning作者 | Rahaf Aljundi, Nikolay Chumerin, Daniel Olmeda Reino連結 | https://arxiv.org/abs/2010.06890 [41] Deep Ensembles for Low-Data Transfer Learning作者 | Basil Mustafa, Carlos Riquelme, Joan Puigcerver, andAndré Susano Pinto, Daniel Keysers, Neil Houlsby連結 | https://arxiv.org/abs/2010.06866 [42] GreedyFool: An Imperceptible Black-box Adversarial Example Attack against Neural Networks作者 | Hui Liu, Bo Zhao, Jiabao Guo, Pengyuan Zhao, Peng Liu連結 | https://arxiv.org/abs/2010.06855 [43] Differential diagnosis and molecular stratification of gastrointestinal stromal tumors on CT images using a radiomics approach作者 | Martijn P.A. Starmans, Milea J.M. Timbergen, Melissa Vos, et al.連結 | https://arxiv.org/abs/2010.06824 備註 | Martijn P.A. Starmans and Milea J.M. Timbergen contributed equally[44] Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout作者 | Zhao Chen, Jiquan Ngiam, Yanping Huang, Thang Luong, Henrik Kretzschmar, Yuning Chai, Dragomir Anguelov連結 | https://arxiv.org/abs/2010.06808 備註 | Conference on Neural Information Processing Systems (NeurIPS) 2020[45] Low-rank Convex/Sparse Thermal Matrix Approximation for Infrared-based Diagnostic System作者 | Bardia Yousefi, Clemente Ibarra Castanedo, Xavier P.V. Maldague連結 | https://arxiv.org/abs/2010.06784 [46] Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision作者 | Hao Tan, Mohit Bansal連結 | https://arxiv.org/abs/2010.06775 備註 | EMNLP 2020 (15 pages)[47] Measuring Visual Generalization in Continuous Control from Pixels作者 | Jake Grigsby, Yanjun Qi連結 | https://arxiv.org/abs/2010.06740 備註 | A total of 17 pages, 8 pages as the main text[48] Random Network Distillation as a Diversity Metric for Both Image and Text Generation作者 | Liam Fowl, Micah Goldblum, Arjun Gupta, Amr Sharaf, Tom Goldstein連結 | https://arxiv.org/abs/2010.06715 [49] Handwriting Quality Analysis using Online-Offline Models作者 | Yahia Hamdi, Hanen Akouaydi, Houcine Boubaker, Adel M. Alimi連結 | https://arxiv.org/abs/2010.06693 [50] A Multi-Modal Method for Satire Detection using Textual and Visual Cues作者 | Lily Li, Or Levi, Pedram Hosseini, David A. Broniatowski連結 | https://arxiv.org/abs/2010.06671 備註 | Accepted to the Third Workshop on NLP for Internet Freedom (NLP4IF): Censorship, Disinformation, and Propaganda. Co-located with COLING 2020[51] LiDAM: Semi-Supervised Learning with Localized Domain Adaptation and Iterative Matching作者 | Qun Liu, Matthew Shreve, Raja Bala連結 | https://arxiv.org/abs/2010.06668 [52] Training independent subnetworks for robust prediction作者 | Marton Havasi, Rodolphe Jenatton, Stanislav Fort, Jeremiah Zhe Liu, Jasper Snoek, Balaji Lakshminarayanan, Andrew M. Dai, Dustin Tran連結 | https://arxiv.org/abs/2010.06610