出品 | 深度學習這件小事公眾號
計算機視覺（12月10日更新版）
[1] Video Deblurring by Fitting to Test Data作者 | Xuanchi Ren, Zian Qian, Qifeng Chen連結 | https://arxiv.org/abs/2012.05228 [2] MorphNet: One-Shot Face Synthesis GAN for Detecting Recognition Bias作者 | Nataniel Ruiz, Barry-John Theobald, Anurag Ranjan, Ahmed Hussein Abdelaziz, Nicholas Apostoloff連結 | https://arxiv.org/abs/2012.05225 [3] Positional Encoding as Spatial Inductive Bias in GANs作者 | Rui Xu, Xintao Wang, Kai Chen, Bolei Zhou, Chen Change Loy連結 | https://arxiv.org/abs/2012.05217 項目連結 | https://nbei.github.io/gan-pos-encoding.html[4] E3D: Event-Based 3D Shape Reconstruction作者 | Alexis Baudron, Winston Wang, Oliver Cossairt, Aggelos Katsaggelos連結 | https://arxiv.org/abs/2012.05214 [5] Predicting Prostate Cancer-Specific Mortality with A.I.-based Gleason Grading作者 | Ellery Wulczyn, Kunal Nagpal, Matthew Symonds, et al.連結 | https://arxiv.org/abs/2012.05197 [6] Rigid and Articulated Point Registration with Expectation Conditional Maximization作者 | Radu Horaud, Florence Forbes, Manuel Yguel, Guillaume Dewaele, Jian Zhang連結 | https://arxiv.org/abs/2012.05191 [7] Physics-Guided Spoof Trace Disentanglement for Generic Face Anti-Spoofing作者 | Yaojie Liu, Xiaoming Liu連結 | https://arxiv.org/abs/2012.05185 [8] Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps作者 | Qi Zhu, Chenyu Gao, Peng Wang, Qi Wu連結 | https://arxiv.org/abs/2012.05153 [9] Self-supervised Human Detection and Segmentation via Multi-view Consensus作者 | Isinsu Katircioglu, Helge Rhodin, Jörg Spörri, Mathieu Salzmann, Pascal Fua連結 | https://arxiv.org/abs/2012.05119 [10] Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments作者 | Zhihao Xia, Michaël Gharbi, Federico Perazzi, Kalyan Sunkavalli, Ayan Chakrabarti連結 | https://arxiv.org/abs/2012.05116 項目連結 | https://www.cse.wustl.edu/~zhihao.xia/deepfnf/[11] Contrastive Transformation for Self-supervised Correspondence Learning作者 | Ning Wang, Wengang Zhou, Houqiang Li連結 | https://arxiv.org/abs/2012.05057 備註 | To appear in AAAI 2021[12] Scene Text Detection with Scribble Lines作者 | Wenqing Zhang, Yang Qiu, Minghui Liao, Rui Zhang, Xiaolin Wei, Xiang Bai連結 | https://arxiv.org/abs/2012.05030 [13] Generating Out of Distribution Adversarial Attack using Latent Space Poisoning作者 | Ujjwal Upadhyay, Prerana Mukherjee連結 | https://arxiv.org/abs/2012.05027 備註 | Submitted to IEEE SPL[14] vLPD-Net: A Registration-aided Domain Adaptation Network for 3D Point Cloud Based Place Recognition作者 | Zhijian Qiao, Hanjiang Hu, Siyuan Chen, Zhe Liu, Zhuowen Shen, Hesheng Wang連結 | https://arxiv.org/abs/2012.05018 [15] Machine Learning for Glacier Monitoring in the Hindu Kush Himalaya作者 | Shimaa Baraka, Benjamin Akera, Bibek Aryal, Tenzing Sherpa, Finu Shresta, Anthony Ortiz, Kris Sankaran, Juan Lavista Ferres, Mir Matin, Yoshua Bengio連結 | https://arxiv.org/abs/2012.05013 備註 | Accepted for a spotlight talk and a poster at the Tackling Climate Change with Machine Learning workshop at NeurIPS 2020[16] Strong but Simple Baseline with Dual-Granularity Triplet Loss for Visible-Thermal Person Re-Identification作者 | Haijun Liu, Yanxia Chai, Xiaoheng Tan, Dong Li, Xichuan Zhou連結 | https://arxiv.org/abs/2012.05010 [17] Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation作者 | Xueyi Li, Tianfei Zhou, Jianwu Li, Yi Zhou, Zhaoxiang Zhang連結 | https://arxiv.org/abs/2012.05007 項目連結 | https://github.com/Lixy1997/Group-WSSS備註 | Accepted to AAAI 2021. [18] Hateful Memes Detection via Complementary Visual and Linguistic Networks作者 | Weibo Zhang, Guihua Liu, Zhuohua Li, Fuqing Zhu連結 | https://arxiv.org/abs/2012.04977 [19] Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network作者 | Denis Coquenet, Clément Chatelain, Thierry Paquet連結 | https://arxiv.org/abs/2012.04961 [20] Have convolutions already made recurrence obsolete for unconstrained handwritten text recognition ?作者 | Denis Coquenet, Yann Soullard, Clement Chatelain, Thierry Paquet連結 | https://arxiv.org/abs/2012.04954 [21] Removing Class Imbalance using Polarity-GAN: An Uncertainty Sampling Approach作者 | Kumari Deepshikha, Anugunj Naman連結 | https://arxiv.org/abs/2012.04937 [22] AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentation作者 | Venice Erin Liong, Thi Ngoc Tho Nguyen, Sergi Widjaja, Dhananjai Sharma, Zhuang Jie Chong連結 | https://arxiv.org/abs/2012.04934 [23] Lipschitz Regularized CycleGAN for Improving Semantic Robustness in Unpaired Image-to-image Translation作者 | Zhiwei Jia, Bodi Yuan, Kangkang Wang, Hong Wu, David Clifford, Zhiqiang Yuan, Hao Su連結 | https://arxiv.org/abs/2012.04932 [24] Robust Facial Landmark Detection by Multi-order Multi-constraint Deep Networks作者 | Jun Wan, Zhihui Lai, Jing Li, Jie Zhou, Can Gao連結 | https://arxiv.org/abs/2012.04927 項目連結 | https://github.com/junwan2014/MMDN-master備註 | This paper has been accepted by TNNLS December 2020. [25] Towards Annotation-Free Evaluation of Cross-Lingual Image Captioning作者 | Aozhu Chen, Xinyi Huang, Hailan Lin, Xirong Li連結 | https://arxiv.org/abs/2012.04925 [26] Kernel Anomalous Change Detection for Remote Sensing Imagery作者 | José A. Padrón-Hidalgo, Valero Laparra, Nathan Longbotham, Gustau Camps-Valls連結 | https://arxiv.org/abs/2012.04920 [27] Progressive Network Grafting for Few-Shot Knowledge Distillation作者 | Chengchao Shen, Xinchao Wang, Youtan Yin, Jie Song, Sihui Luo, Mingli Song連結 | https://arxiv.org/abs/2012.04915 備註 | Accepted to AAAI 2021[28] Generative Data Augmentation for Vehicle Detection in Aerial Images作者 | Hilmi Kumdakcı, Cihan Öngün, Alptekin Temizel連結 | https://arxiv.org/abs/2012.04902 備註 | Workshop on Analysis of Aerial Motion Imagery (WAAMI 2020) in conjunction with 25th International Conference on Pattern Recognition (ICPR 2020)[29] DS-Net: Dynamic Spatiotemporal Network for Video Salient Object Detection作者 | Yuting Su, Weikang Wang, Jing Liu, Peiguang Jing, Xiaokang Yang連結 | https://arxiv.org/abs/2012.04886 [30] JANUS: Benchmarking Commercial and Open-Source Cloud and Edge Platforms for Object and Anomaly Detection Workloads作者 | Karthick Shankar, Pengcheng Wang, Ran Xu, Ashraf Mahgoub, Somali Chaterji連結 | https://arxiv.org/abs/2012.04880 備註 | Appeared at the IEEE Cloud 2020 conference. 10 pages[31] Deep Lesion Tracker: Monitoring Lesions in 4D Longitudinal Imaging Studies作者 | Jinzheng Cai, Youbao Tang, Ke Yan, Adam P. Harrison, Jing Xiao, Gigin Lin, Le Lu連結 | https://arxiv.org/abs/2012.04872 備註 | Main manuscript: 11 pages, 4 figures, and 5 tables. Supplementary materials: 6 pages, 5 figures, and 1 table. Under review for publication[32] SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data作者 | Shaoli Huang, Xinchao Wang, Dacheng Tao連結 | https://arxiv.org/abs/2012.04846 備註 | Accepted by AAAI2021[33] Improving the Fairness of Deep Generative Models without Retraining作者 | Shuhan Tan, Yujun Shen, Bolei Zhou連結 | https://arxiv.org/abs/2012.04842 項目連結 | https://genforce.github.io/fairgen/[34] One-Vote Veto: A Self-Training Strategy for Low-Shot Learning of a Task-Invariant Embedding to Diagnose Glaucoma作者 | Rui Fan, Christopher Bowd, Nicole Brye, Mark Christopher, Robert N. Weinreb, David Kriegman, Linda Zangwill連結 | https://arxiv.org/abs/2012.04841 [35] Deep Unsupervised Image Anomaly Detection: An Information Theoretic Framework作者 | Fei Ye, Huangjie Zheng, Chaoqin Huang, Ya Zhang連結 | https://arxiv.org/abs/2012.04837 [36] A Topological Filter for Learning with Label Noise作者 | Pengxiang Wu, Songzhu Zheng, Mayank Goswami, Dimitris Metaxas, Chao Chen連結 | https://arxiv.org/abs/2012.04835 [37] Semi-supervised Active Learning for Instance Segmentation via Scoring Predictions作者 | Jun Wang, Shaoguo Wen, Kaixing Chen, Jianghua Yu, Xin Zhou, Peng Gao, Changsheng Li, Guotong Xie連結 | https://arxiv.org/abs/2012.04829 備註 | accepted for presentation at BMVC2020[38] Two-phase Pseudo Label Densification for Self-training based Domain Adaptation作者 | Inkyu Shin, Sanghyun Woo, Fei Pan, InSo Kweon連結 | https://arxiv.org/abs/2012.04828 備註 | Accepted to ECCV 2020[39] Deep Learning based Multi-Modal Sensing for Tracking and State Extraction of Small Quadcopters作者 | Zhibo Zhang, Chen Zeng, Maulikkumar Dhameliya, Souma Chowdhury, Rahul Rai連結 | https://arxiv.org/abs/2012.04794 [40] You Only Need Adversarial Supervision for Semantic Image Synthesis作者 | Vadim Sushko, Edgar Schönfeld, Dan Zhang, Juergen Gall, Bernt Schiele, Anna Khoreva連結 | https://arxiv.org/abs/2012.04781 [41] Mitigating the Impact of Adversarial Attacks in Very Deep Networks作者 | Mohammed Hassanin, Ibrahim Radwan, Nour Moustafa, Murat Tahtali, Neeraj Kumar連結 | https://arxiv.org/abs/2012.04750 [42] Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments作者 | Siyan Dong, Qingnan Fan, He Wang, Ji Shi, Li Yi, Thomas Funkhouser, Baoquan Chen, Leonidas Guibas連結 | https://arxiv.org/abs/2012.04746 [43] CARAFE++: Unified Content-Aware ReAssembly of FEatures作者 | Jiaqi Wang, Kai Chen, Rui Xu, Ziwei Liu, Chen Change Loy, Dahua Lin連結 | https://arxiv.org/abs/2012.04733 備註 | Technical Report. Extended journal version of the conference paper that appeared as arXiv:1905.02188[44] Long Term Motion Prediction Using Keyposes作者 | Sena Kiciroglu, Wei Wang, Mathieu Salzmann, Pascal Fua連結 | https://arxiv.org/abs/2012.04731 [45] Canonical Capsules: Unsupervised Capsules in Canonical Pose作者 | Weiwei Sun, Andrea Tagliasacchi, Boyang Deng, Sara Sabour, Soroosh Yazdani, Geoffrey Hinton, Kwang Moo Yi連結 | https://arxiv.org/abs/2012.04718 備註 | The first two authors contributed equally to this work[46] ODFNet: Using orientation distribution functions to characterize 3D point clouds作者 | Yusuf H. Sahin, Alican Mertan, Gozde Unal連結 | https://arxiv.org/abs/2012.04708 備註 | The paper is under consideration at Computer Vision and Image Understanding[47] Locally optimal detection of stochastic targeted universal adversarial perturbations作者 | Amish Goel, Pierre Moulin連結 | https://arxiv.org/abs/2012.04692 備註 | Submitted to ICASSP 2021[48] A Dataset and Application for Facial Recognition of Individual Gorillas in Zoo Environments作者 | Otto Brookes, Tilo Burghardt連結 | https://arxiv.org/abs/2012.04689 [49] Tactile Object Pose Estimation from the First Touch with Geometric Contact Rendering作者 | Maria Bauza, Eric Valls, Bryan Lim, Theo Sechopoulos, Alberto Rodriguez連結 | https://arxiv.org/abs/2012.05205 視頻連結 | https://youtu.be/2ygtSJTmo08[50] Convex Regularization Behind Neural Reconstruction作者 | Arda Sahiner, Morteza Mardani, Batu Ozturkler, Mert Pilanci, John Pauly連結 | https://arxiv.org/abs/2012.05169 [51] Towards Zero-shot Cross-lingual Image Retrieval作者 | Pranav Aggarwal, Ajinkya Kale連結 | https://arxiv.org/abs/2012.05107 [52] COVID-19 Detection in Chest X-Ray Images using a New Channel Boosted CNN作者 | Saddam Hussain Khan, Anabia Sohail, Asifullah Khan連結 | https://arxiv.org/abs/2012.05073 [53] Driving Behavior Explanation with Multi-level Fusion作者 | Hédi Ben-Younes, Éloi Zablocki, Patrick Pérez, Matthieu Cord連結 | https://arxiv.org/abs/2012.04983 備註 | Accepted at NeurIPS Workshop ML4AD 2020[54] Automated Scoring of Nuclear Pleomorphism Spectrum with Pathologist-level Performance in Breast Cancer作者 | Caner Mercan, Maschenka Balkenhol, Roberto Salgado, Mark Sherman, Philippe Vielh, Willem Vreuls, Antonio Polonia, Hugo M. Horlings, Wilko Weichert, Jodi M. Carter, Peter Bult, Matthias Christgen, Carsten Denkert, Koen van de Vijver, Jeroen van der Laak, Francesco Ciompi連結 | https://arxiv.org/abs/2012.04974 [55] Conjugate Mixture Models for Clustering Multimodal Data作者 | Vasil Khalidov, Florence Forbes, Radu Horaud連結 | https://arxiv.org/abs/2012.04951 [56] Improving Gradient Flow with Unrolled Highway Expectation Maximization作者 | Chonghyuk Song, Eunseok Kim, Inwook Shim連結 | https://arxiv.org/abs/2012.04926 備註 | Accepted at AAAI 2021. Preprint[57] ESAD: End-to-end Deep Semi-supervised Anomaly Detection作者 | Chaoqin Huang, Fei Ye, Ya Zhang, Yan-Feng Wang, Qi Tian連結 | https://arxiv.org/abs/2012.04905 [58] AIDE: Annotation-efficient deep learning for automatic medical image segmentation作者 | Cheng Li, Rongpin Wang, Zaiyi Liu, Meiyun Wang, Hongna Tan, Yaping Wu, Xinfeng Liu, Hui Sun, Rui Yang, Xin Liu, Ismail Ben Ayed, Hairong Zheng, Hanchuan Peng, Shanshan Wang連結 | https://arxiv.org/abs/2012.04885 [59] Discovering Clinically Meaningful Shape Features for the Analysis of Tumor Pathology Images作者 | Esteban Fernández Morales, Cong Zhang, Guanghua Xiao, Chul Moon, Qiwei Li連結 | https://arxiv.org/abs/2012.04878 [60] Skillearn: Machine Learning Inspired by Humans' Learning Skills作者 | Pengtao Xie, Xuefeng Du, Hao Ban連結 | https://arxiv.org/abs/2012.04863 備註 | arXiv admin note: substantial text overlap with arXiv:2011.15102[61] Machine Learning for Cataract Classification and Grading on Ophthalmic Imaging Modalities: A Survey作者 | Xiaoqing Zhang, JianSheng Fang, Yan Hu, Yanwu Xu, Risa Higashita, Jiang Liu連結 | https://arxiv.org/abs/2012.04830 [62] Conditional Generation of Medical Images via Disentangled Adversarial Inference作者 | Mohammad Havaei, Ximeng Mao, Yiping Wang, Qicheng Lao連結 | https://arxiv.org/abs/2012.04764 [63] 2-Step Sparse-View CT Reconstruction with a Domain-Specific Perceptual Network作者 | Haoyu Wei, Florian Schiffers, Tobias Würfl, Daming Shen, Daniel Kim, Aggelos K. Katsaggelos, Oliver Cossairt連結 | https://arxiv.org/abs/2012.04743 [64] Edited Media Understanding: Reasoning About Implications of Manipulated Images作者 | Jeff Da, Maxwell Forbes, Rowan Zellers, Anthony Zheng, Jena D. Hwang, Antoine Bosselut, Yejin Choi連結 | https://arxiv.org/abs/2012.04726 [65] 3D Graph Anatomy Geometry-Integrated Network for Pancreatic Mass Segmentation, Diagnosis, and Quantitative Patient Management作者 | Tianyi Zhao, Kai Cao, Jiawen Yao, Isabella Nogues, Le Lu, Lingyun Huang, Jing Xiao, Zhaozheng Yin, Ling Zhang連結 | https://arxiv.org/abs/2012.04701 [66] MOCA: A Modular Object-Centric Approach for Interactive Instruction Following作者 | Kunal Pratap Singh, Suvaansh Bhambri, Byeonghwi Kim, Roozbeh Mottaghi, Jonghyun Choi連結 | https://arxiv.org/abs/2012.03208