每日论文速递：计算机视觉相关（9月14日更新版）

作者：Hsu
转载自：深度学习这件小事
原文链接：

计算机视觉（9月14日更新版）

[1] Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN作者 | Badour AlBahar, Jingwan Lu, Jimei Yang, Zhixin Shu, Eli Shechtman, Jia-Bin Huang链接 | https://arxiv.org/abs/2109.06166 项目链接 | https://pose-with-style.github.io/备注 | SIGGRAPH Asia 2021.

[2] CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation作者 | Tongkun Xu, Weihua Chen, Pichao Wang, Fan Wang, Hao Li, Rong Jin链接 | https://arxiv.org/abs/2109.06165

[3] On the Sins of Image Synthesis Loss for Self-supervised Depth Estimation作者 | Zhaoshuo Li, Nathan Drenkow, Hao Ding, et al.链接 | https://arxiv.org/abs/2109.06163 备注 | preprint

[4] Single-stage Keypoint-based Category-level Object Pose Estimation from an RGB Image作者 | Yunzhi Lin, Jonathan Tremblay, Stephen Tyree, Patricio A. Vela, Stan Birchfield链接 | https://arxiv.org/abs/2109.06161 备注 | submitted to ICRA 2022

[5] Image Shape Manipulation from a Single Augmented Training Sample作者 | Yael Vinker, Eliahu Horwitz, Nir Zabari, Yedid Hoshen链接 | https://arxiv.org/abs/2109.06151 备注 | ICCV 2021 (Oral). arXiv admin note: text overlap with arXiv:2007.01289

[6] DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection作者 | Steven Lang, Fabrizio Ventola, Kristian Kersting链接 | https://arxiv.org/abs/2109.06148

[7] Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color作者 | Mostafa Abdou, Artur Kulmizev, Daniel Hershcovich, Stella Frank, Ellie Pavlick, Anders Søgaard链接 | https://arxiv.org/abs/2109.06129 备注 | CoNLL 2021

[8] Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question Answering作者 | Jihyung Kil, Cheng Zhang, Dong Xuan, Wei-Lun Chao链接 | https://arxiv.org/abs/2109.06122 备注 | Accepted to EMNLP 2021

[9] Weakly Supervised Person Search with Region Siamese Networks作者 | Chuchu Han, Kai Su, Dongdong Yu, Zehuan Yuan, Changxin Gao, Nong Sang, Yi Yang, Changhu Wang链接 | https://arxiv.org/abs/2109.06109 备注 | Accepted by ICCV 2021

[10] Single-stream CNN with Learnable Architecture for Multi-source Remote Sensing Data作者 | Yi Yang, Daoye Zhu, Tengteng Qu, Qiangyu Wang, Fuhu Ren, Chengqi Cheng链接 | https://arxiv.org/abs/2109.06094

[11] On Pursuit of Designing Multi-modal Transformer for Video Grounding作者 | Meng Cao, Long Chen, Mike Zheng Shou, Can Zhang, Yuexian Zou链接 | https://arxiv.org/abs/2109.06085 备注 | Accepted by Conference on Empirical Methods in Natural Language Processing (EMNLP 2021)

[12] Semantics-Guided Contrastive Network for Zero-Shot Object detection作者 | Caixia Yan, Xiaojun Chang, Minnan Luo, Huan Liu, Xiaoqin Zhang, Qinghua Zheng链接 | https://arxiv.org/abs/2109.06062 备注 | 15 pages

[13] Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting作者 | Zian Wang, Jonah Philion, Sanja Fidler, Jan Kautz链接 | https://arxiv.org/abs/2109.06061 备注 | ICCV 2021 (Oral Presentation)

[14] Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions作者 | Xiangtan Lin, Pengzhen Ren, Chung-Hsing Yeh, Lina Yao, Andy Song, Xiaojun Chang链接 | https://arxiv.org/abs/2109.06057 备注 | 27 pages

[15] Learning to Ground Visual Objects for Visual Dialog作者 | Feilong Chen, Xiuyi Chen, Can Xu, Daxin Jiang链接 | https://arxiv.org/abs/2109.06013 备注 | Findings of the Association for Computational Linguistics: EMNLP 2021

[16] Mutual Supervision for Dense Object Detection作者 | Ziteng Gao, Limin Wang, Gangshan Wu链接 | https://arxiv.org/abs/2109.05986 备注 | ICCV 2021 camera ready version

[17] Task Guided Compositional Representation Learning for ZDA作者 | Shuang Liu, Mete Ozay链接 | https://arxiv.org/abs/2109.05934

[18] Vision-based system identification and 3D keypoint discovery using dynamics constraints作者 | Miguel Jaques, Martin Asenov, Michael Burke, Timothy Hospedales链接 | https://arxiv.org/abs/2109.05928

[19] Evolving Architectures with Gradient Misalignment toward Low Adversarial Transferability作者 | Kevin Richard G. Operiano, Wanchalerm Pora, Hitoshi Iba, Hiroshi Kera链接 | https://arxiv.org/abs/2109.05919 备注 | 23 pages, 4 figures

[20] Nonlocal Patch-Based Fully-Connected Tensor Network Decomposition for Remote Sensing Image Inpainting作者 | Wen-Jie Zheng, Xi-Le Zhao, Yu-Bang Zheng, Zhi-Feng Pang链接 | https://arxiv.org/abs/2109.05889

[21] Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images作者 | Size Wu, Sheng Jin, Wentao Liu, Lei Bai, Chen Qian, Dong Liu, Wanli Ouyang链接 | https://arxiv.org/abs/2109.05885 备注 | Accepted by ICCV'2021

[22] Conditional MoCoGAN for Zero-Shot Video Generation作者 | Shun Kimura, Kazuhiko Kawamoto链接 | https://arxiv.org/abs/2109.05864 备注 | 5 pages, 4 figure

[23] Adversarial Bone Length Attack on Action Recognition作者 | Nariki Tanaka, Hiroshi Kera, Kazuhiko Kawamoto链接 | https://arxiv.org/abs/2109.05830 备注 | 11 pages, 8 figures

[24] Variational Disentanglement for Domain Generalization作者 | Yufei Wang, Haoliang Li, Lap-Pui Chau, Alex C. Kot链接 | https://arxiv.org/abs/2109.05826

[25] Improving Robustness of Adversarial Attacks Using an Affine-Invariant Gradient Estimator作者 | Wenzhao Xiang, Hang Su, Chang Liu, Yandong Guo, Shibao Zheng链接 | https://arxiv.org/abs/2109.05820

[26] Leveraging Clinical Characteristics for Improved Deep Learning-Based Kidney Tumor Segmentation on CT作者 | Christina B. Lund, Bas H. M. van der Velden链接 | https://arxiv.org/abs/2109.05816 备注 | Submitted to the Kidney and Kidney Tumor Segmentation Challenge (KiTS21), MICCAI 2021

[27] MLFW: A Database for Face Recognition on Masked Faces作者 | Chengrui Wang, Han Fang, Yaoyao Zhong, Weihong Deng链接 | https://arxiv.org/abs/2109.05804

[28] DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis作者 | Tiange Xiang, Yang Song, Chaoyi Zhang, Dongnan Liu, Mei Chen, Fan Zhang, Heng Huang, Lauren O'Donnell, Weidong Cai链接 | https://arxiv.org/abs/2109.05788

[29] The State of the Art when using GPUs in Devising Image Generation Methods Using Deep Learning作者 | Yasuko Kawahata链接 | https://arxiv.org/abs/2109.05783 备注 | 13 pages

[30] Deep Joint Source-Channel Coding for Multi-Task Network作者 | Mengyang Wang, Zhicong Zhang, Jiahui Li, Mengyao Ma, Xiaopeng Fan链接 | https://arxiv.org/abs/2109.05779 备注 | submitted to signal processing letters

[31] Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks作者 | Chunzhi Gu, Yan Zhao, Chao Zhang链接 | https://arxiv.org/abs/2109.05776

[32] Global-Local Dynamic Feature Alignment Network for Person Re-Identification作者 | Zhangqiang Ming, Yong Yang, Xiaoyong Wei, Jianrong Yan, Xiangkun Wang, Fengjie Wang, Min Zhu链接 | https://arxiv.org/abs/2109.05759

[33] Adversarially Trained Object Detector for Unsupervised Domain Adaptation作者 | Kazuma Fujii, Hiroshi Kera, Kazuhiko Kawamoto链接 | https://arxiv.org/abs/2109.05751

[34] Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization作者 | Jingtang Liang, Xiaodong Cun, Chi-Man Pun链接 | https://arxiv.org/abs/2109.05750

[35] Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning作者 | Chi Zhang, Henghui Ding, Guosheng Lin, Ruibo Li, Changhu Wang, Chunhua Shen链接 | https://arxiv.org/abs/2109.05749 备注 | Accepted by ICCV2021

[36] ChangeChip: A Reference-Based Unsupervised Change Detection for PCB Defect Detection作者 | Yehonatan Fridman, Matan Rusanovsky, Gal Oren链接 | https://arxiv.org/abs/2109.05746 项目链接 | https://github.com/Scientific-Computing-Lab-NRCN/ChangeChip备注 | The sources of ChangeChip, as well as CD-PCB

[37] Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation作者 | Zechen Bai, Yuta Nakashima, Noa Garcia链接 | https://arxiv.org/abs/2109.05743 备注 | ICCV 2021

[38] HCDG: A Hierarchical Consistency Framework for Domain Generalization on Medical Image Segmentation作者 | Yijun Yang, Shujun Wang, Pheng-Ann Heng, Lequan Yu链接 | https://arxiv.org/abs/2109.05742

[39] Efficient Tensor Completion via Element-wise Weighted Low-rank Tensor Train with Overlapping Ket Augmentation作者 | Yang Zhang, Yao Wang, Zhi Han, Xi'ai Chen, Yandong Tang链接 | https://arxiv.org/abs/2109.05736

[40] ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment作者 | Yangyu Huang, Hao Yang, Chong Li, Jongyoo Kim, Fangyun Wei链接 | https://arxiv.org/abs/2109.05721 备注 | ICCV 2021

[41] Low-Shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categories作者 | Fait Poms, Vishnu Sarukkai, Ravi Teja Mullapudi, Nimit S. Sohoni, William R. Mark, Deva Ramanan, Kayvon Fatahalian链接 | https://arxiv.org/abs/2109.05720 备注 | Accepted to ICCV 2021; 12 pages, 12 figures

[42] Fine-Grained Few Shot Learning with Foreground Object Transformation作者 | Chaofei Wang, Shiji Song, Qisen Yang, Xiang Li, Gao Huang链接 | https://arxiv.org/abs/2109.05719 备注 | Accepted by Neurocomputing

[43] CarNet: A Lightweight and Efficient Encoder-Decoder Architecture for High-quality Road Crack Detection作者 | Kai Li, Yingjie Tian, Zhiquan Qi链接 | https://arxiv.org/abs/2109.05707 备注 | 13 pages, 14 figures, 8 tables

[44] PAT: Pseudo-Adversarial Training For Detecting Adversarial Videos作者 | Nupur Thakur, Baoxin Li链接 | https://arxiv.org/abs/2109.05695 备注 | 7 pages,5 figures

[45] Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition作者 | Jian Jia, Xiaotang Chen, Kaiqi Huang链接 | https://arxiv.org/abs/2109.05686 备注 | Accepted to ICCV 2021

[46] Online Unsupervised Learning of Visual Representations and Categories作者 | Mengye Ren, Tyler R. Scott, Michael L. Iuzzolino, Michael C. Mozer, Richard Zemel链接 | https://arxiv.org/abs/2109.05675 备注 | 29 pages

[47] FaceGuard: Proactive Deepfake Detection作者 | Yuankun Yang, Chenyue Liang, Hongyu He, Xiaoyu Cao, Neil Zhenqiang Gong链接 | https://arxiv.org/abs/2109.05673

[48] Shape-Biased Domain Generalization via Shock Graph Embeddings作者 | Maruthi Narayanan, Vickram Rajendran, Benjamin Kimia链接 | https://arxiv.org/abs/2109.05671 备注 | Accepted to ICCV 2021

[49] UMPNet: Universal Manipulation Policy Network for Articulated Objects作者 | Zhenjia Xu, Zhanpeng He, Shuran Song链接 | https://arxiv.org/abs/2109.05668

[50] CANS: Communication Limited Camera Network Self-Configuration for Intelligent Industrial Surveillance作者 | Jingzheng Tu, Qimin Xu, Cailian Chen链接 | https://arxiv.org/abs/2109.05665 备注 | 6 pages, 11 figures

[51] Unsupervised domain adaptation for cross-modality liver segmentation via joint adversarial learning and self-learning作者 | Jin Hong, Simon Chun Ho Yu, Weitian Chen链接 | https://arxiv.org/abs/2109.05664

[52] Generating Datasets of 3D Garments with Sewing Patterns作者 | Maria Korosteleva, Sung-Hee Lee链接 | https://arxiv.org/abs/2109.05633 备注 | To appear in NeurIPS 2021 Datasets and Benchmarks Track

[53] MSGDD-cGAN: Multi-Scale Gradients Dual Discriminator Conditional Generative Adversarial Network作者 | Mohammadreza Naderi, Zahra Nabizadeh, Nader Karimi, Shahram Shirani, Shadrokh Samavi链接 | https://arxiv.org/abs/2109.05614 备注 | 8 pages, 6 figures

[54] Multiresolution Deep Implicit Functions for 3D Shape Representation作者 | Zhang Chen, Yinda Zhang, Kyle Genova, et al.链接 | https://arxiv.org/abs/2109.05591 备注 | 8 pages of main paper, 10 pages of supplementary. Accepted by ICCV'21

[55] U-Net Convolutional Network for Recognition of Vessels and Materials in Chemistry Lab作者 | Zhihao Shang, Di Bo链接 | https://arxiv.org/abs/2109.05585

[56] MovieCuts: A New Dataset and Benchmark for Cut Type Recognition作者 | Alejandro Pardo, Fabian Caba Heilbron, Juan León Alcázar, Ali Thabet, Bernard Ghanem链接 | https://arxiv.org/abs/2109.05569 项目链接 | https://www.alejandropardo.net/publication/moviecuts/

[57] PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds作者 | Xiaoxue Chen, Hao Zhao, Guyue Zhou, Ya-Qin Zhang链接 | https://arxiv.org/abs/2109.05566 项目链接 | https://github.com/OPEN-AIR-SUN/PQ-Transformer

[58] SphereFace Revived: Unifying Hyperspherical Face Recognition作者 | Weiyang Liu, Yandong Wen, Bhiksha Raj, Rita Singh, Adrian Weller链接 | https://arxiv.org/abs/2109.05565 备注 | Technical Report (15 pages)

[59] Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification作者 | Qi Wang, Sikai Bai, Junyu Gao, Yuan Yuan, Xuelong Li链接 | https://arxiv.org/abs/2109.05542

[60] DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval作者 | Aichun Zhu, Zijie Wang, Yifeng Li, Xili Wan, Jing Jin, Tian Wang, Fangqiang Hu, Gang Hua链接 | https://arxiv.org/abs/2109.05534 备注 | Accepted by ACM MM'21

[61] An Unsupervised Deep-Learning Method for Fingerprint Classification: the CCAE Network and the Hybrid Clustering Strategy作者 | Yue-Jie Hou, Zai-Xin Xie, Jian-Hu, Yao-Shen, Chi-Chun Zhou链接 | https://arxiv.org/abs/2109.05526

[62] A Decidability-Based Loss Function作者 | Pedro Silva, Gladston Moreira, Vander Freitas, Rodrigo Silva, David Menotti, Eduardo Luz链接 | https://arxiv.org/abs/2109.05524 备注 | 23 pages, 7 figures. Paper submitted to Pattern Recognition Letters (PRL)

[63] Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval作者 | Zhihao Fan, Zhongyu Wei, Zejun Li, Siyuan Wang, Haijun Shan, Xuanjing Huang, Jianqing Fan链接 | https://arxiv.org/abs/2109.05523

[64] LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection作者 | Ryoya Katafuchi, Terumasa Tokunaga链接 | https://arxiv.org/abs/2109.05493

[65] ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis作者 | Kailin Li, Lixin Yang, Xinyu Zhan, Jun Lv, Wenqiang Xu, Jiefeng Li, Cewu Lu链接 | https://arxiv.org/abs/2109.05488

[66] Facial Anatomical Landmark Detection using Regularized Transfer Learning with Application to Fetal Alcohol Syndrome Recognition作者 | Zeyu Fu, Jianbo Jiao, Michael Suttie, J. Alison Noble链接 | https://arxiv.org/abs/2109.05485 备注 | To appear in IEEE journal of Biomedical and Health Informatics 2021

[67] What happens in Face during a facial expression? Using data mining techniques to analyze facial expression motion vectors作者 | Mohamad Roshanzamir, Roohallah Alizadehsani, Mahdi Roshanzamir, Afshin Shoeibi, Juan M. Gorriz, Abbas Khosrave, Saeid Nahavandi链接 | https://arxiv.org/abs/2109.05457

[68] Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception作者 | Xinge Zhu, Hui Zhou, Tai Wang, Fangzhou Hong, Wei Li, Yuexin Ma, Hongsheng Li, Ruigang Yang, Dahua Lin链接 | https://arxiv.org/abs/2109.05441 项目链接 | https://github.com/xinge008/Cylinder3D备注 | Accepted by TPAMI 2021;

[69] Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search作者 | Jialu Wang, Yang Liu, Xin Eric Wang链接 | https://arxiv.org/abs/2109.05433 备注 | 14 pages, EMNLP 2021

[70] Prioritized Subnet Sampling for Resource-Adaptive Supernet Training作者 | Bohong Chen, Mingbao Lin, Liujuan Cao, Jianzhuang Liu, Qixiang Ye, Baochang Zhang, Wei Zeng, Yonghong Tian, Rongrong Ji链接 | https://arxiv.org/abs/2109.05432

[71] Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?作者 | Chuanxin Tang, Yucheng Zhao, Guangting Wang, Chong Luo, Wenxuan Xie, Wenjun Zeng链接 | https://arxiv.org/abs/2109.05422

[72] Challenges and Solutions in DeepFakes作者 | Jatin Sharma, Sahil Sharma链接 | https://arxiv.org/abs/2109.05397 备注 | 6 Figures and 11 Tables

[73] Border-SegGCN: Improving Semantic Segmentation by Refining the Border Outline using Graph Convolutional Network作者 | Naina Dhingra, George Chogovadze, Andreas Kunz链接 | https://arxiv.org/abs/2109.05353 备注 | 8 pages

[74] DeepPyram: Enabling Pyramid View and Deformable Pyramid Reception for Semantic Segmentation in Cataract Surgery Videos作者 | Negin Ghamsarian, Mario Taschwer, klaus Schoeffmann链接 | https://arxiv.org/abs/2109.05352 备注 | 12 pages, 10 figures

[75] BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation作者 | Naina Dhingra, Florian Ritter, Andreas Kunz链接 | https://arxiv.org/abs/2109.05346 备注 | 8 pages, 7 supplementary pages

[76] Class-Distribution-Aware Calibration for Long-Tailed Visual Recognition作者 | Mobarakol Islam, Lalithkumar Seenivasan, Hongliang Ren, Ben Glocker链接 | https://arxiv.org/abs/2109.05263 备注 | Presented at the ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning

[77] Learning Statistical Representation with Joint Deep Embedded Clustering作者 | Mina Rezaei, Emilio Dorigatti, David Ruegamer, Bernd Bischl链接 | https://arxiv.org/abs/2109.05232

[78] Evaluating Computer Vision Techniques for Urban Mobility on Large-Scale, Unconstrained Roads作者 | Harish Rithish, Raghava Modhugu, Ranjith Reddy, Rohit Saluja, C.V. Jawahar链接 | https://arxiv.org/abs/2109.05226 备注 | 8 pages, 8 figures

[79] Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence作者 | Juhong Min, Seungwook Kim, Minsu Cho链接 | https://arxiv.org/abs/2109.05221 备注 | submitted to TPAMI. arXiv admin note: substantial text overlap with arXiv:2103.16831

[80] Bornon: Bengali Image Captioning with Transformer-based Deep learning approach作者 | Faisal Muhammad Shah, Mayeesha Humaira, Md Abidur Rahman Khan Jim, Amit Saha Ami, Shimul Paul链接 | https://arxiv.org/abs/2109.05218

[81] RobustART: Benchmarking Robustness on Architecture Design and Training Techniques作者 | Shiyu Tang, Ruihao Gong, Yan Wang, Aishan Liu, Jiakai Wang, Xinyun Chen, Fengwei Yu, Xianglong Liu, Dawn Song, Alan Yuille, Philip H.S. Torr, Dacheng Tao链接 | https://arxiv.org/abs/2109.05211

[82] Pyramid Hybrid Pooling Quantization for Efficient Fine-Grained Image Retrieval作者 | Ziyun Zeng, Jinpeng Wang, Bin Chen, Tao Dai, Shu-Tao Xia链接 | https://arxiv.org/abs/2109.05206

[83] Contrastive Quantization with Code Memory for Unsupervised Image Retrieval作者 | Jinpeng Wang, Ziyun Zeng, Bin Chen, Tao Dai, Shu-Tao Xia链接 | https://arxiv.org/abs/2109.05205

[84] Conditional Generation of Synthetic Geospatial Images from Pixel-level and Feature-level Inputs作者 | Xuerong Xiao, Swetava Ganguli, Vipul Pandey链接 | https://arxiv.org/abs/2109.05201 备注 | Extended abstract accepted for presentation at BayLearn 2021. 3 pages, 2 figures

[85] A Self-Supervised Deep Framework for Reference Bony Shape Estimation in Orthognathic Surgical Planning作者 | Deqiang Xiao, Hannah Deng, Tianshu Kuang, et al.链接 | https://arxiv.org/abs/2109.05191

[86] Partially-supervised novel object captioning leveraging context from paired data作者 | Shashank Bujimalla, Mahesh Subedar, Omesh Tickoo链接 | https://arxiv.org/abs/2109.05115 备注 | 8 pages, 4 figures, 5 tables

[87] Preliminary Wildfire Detection Using State-of-the-art PTZ (Pan, Tilt, Zoom) Camera Technology and Convolutional Neural Networks作者 | Samarth Shah链接 | https://arxiv.org/abs/2109.05083 备注 | 12 pages, 7 figures

[88] A semi-supervised self-training method to develop assistive intelligence for segmenting multiclass bridge elements from inspection videos作者 | Muhammad Monjurul Karim, Ruwen Qin, Zhaozheng Yin, enda Chen链接 | https://arxiv.org/abs/2109.05078 备注 | Published in Structural Health Monitoring

[89] Instance-Conditioned GAN作者 | Arantxa Casanova, Marlène Careil, Jakob Verbeek, Michal Drozdzal, Adriana Romero-Soriano链接 | https://arxiv.org/abs/2109.05070

[90] Blood vessel segmentation in en-face OCTA images: a frequency based method作者 | Anna Breger, Felix Goldbach, Bianca S. Gerendas, Ursula Schmidt-Erfurth, Martin Ehler链接 | https://arxiv.org/abs/2109.06116

[91] The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networks作者 | Alexander Bastounis, Anders C Hansen, Verner Vlačić链接 | https://arxiv.org/abs/2109.06098 备注 | 29 pages, 1 figure

[92] Balancing the Budget: Feature Selection and Tracking for Multi-Camera Visual-Inertial Odometry作者 | Lintong Zhang, David Wisth, Marco Camurri, Maurice Fallon链接 | https://arxiv.org/abs/2109.05975 项目链接 | https://youtu.be/cLWeAT72e0U

[93] Low-Light Image Enhancement with Normalizing Flow作者 | Yufei Wang, Renjie Wan, Wenhan Yang, Haoliang Li, Lap-Pui Chau, Alex C. Kot链接 | https://arxiv.org/abs/2109.05923

[94] WeakSTIL: Weak whole-slide image level stromal tumor infiltrating lymphocyte scores are all you need作者 | Yoni Schirris, Mendel Engelaer, Andreas Panteli, Hugo Mark Horlings, Efstratios Gavves, Jonas Teuwen链接 | https://arxiv.org/abs/2109.05892

[95] IceNet for Interactive Contrast Enhancement作者 | Keunsoo Ko, Chang-Su Kim链接 | https://arxiv.org/abs/2109.05838 备注 | 11 pages, 9 figures, 3 tables. This paper has been submitted to IEEE Access. Copyright may change without notice

[96] Self supervised learning improves dMMR/MSI detection from histology slides across multiple cancers作者 | Charlie Saillard, Olivier Dehaene, Tanguy Marchand, et al.链接 | https://arxiv.org/abs/2109.05819 备注 | Accepted for poster and oral presentation at the MICCAI 2021 COMPAY Workshop (submitted the 19th of July 2021)

[97] DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture作者 | Kaichen Zhou, Lanqing Hong, Shoukang Hu, Fengwei Zhou, Binxin Ru, Jiashi Feng, Zhenguo Li链接 | https://arxiv.org/abs/2109.05765

[98] Domain and Content Adaptive Convolution for Domain Generalization in Medical Image Segmentation作者 | Shishuai Hu, Zehui Liao, Jianpeng Zhang, Yong Xia链接 | https://arxiv.org/abs/2109.05676

[99] Real-Time EMG Signal Classification via Recurrent Neural Networks作者 | Reza Bagherian Azhiri, Mohammad Esmaeili, Mehrdad Nourani链接 | https://arxiv.org/abs/2109.05674

[100] Differential Diagnosis of Frontotemporal Dementia and Alzheimer's Disease using Generative Adversarial Network作者 | Ma Da, Lu Donghuan, Popuri Karteek, Beg Mirza Faisal链接 | https://arxiv.org/abs/2109.05627

[101] A Joint Graph and Image Convolution Network for Automatic Brain Tumor Segmentation作者 | Camillo Saueressig, Adam Berkley, Reshma Munbodh, Ritambhara Singh链接 | https://arxiv.org/abs/2109.05580 备注 | 9 pages, 3 figures, submitted to BrainLes Workshop (MICCAI 2021) as part of BraTS2021 challenge

[102] BioLCNet: Reward-modulated Locally Connected Spiking Neural Networks作者 | Hafez Ghaemi, Erfan Mirzaei, Mahbod Nouri, Saeed Reza Kheradpisheh链接 | https://arxiv.org/abs/2109.05539 备注 | 8 pages, 5 figures

[103] Towards Robust Monocular Visual Odometry for Flying Robots on Planetary Missions作者 | Martin Wudenka, Marcus G. Müller, Nikolaus Demmel, Armin Wedler, Rudolph Triebel, Daniel Cremers, Wolfgang Stürzl链接 | https://arxiv.org/abs/2109.05509 项目链接 | https://github.com/DLR-RM/granite备注 | Accepted to IROS 2021. Updated version corresponding to IROS camera-ready.

[104] Check Your Other Door! Establishing Backdoor Attacks in the Frequency Domain作者 | Hasan Abed Al Kader Hammoud, Bernard Ghanem链接 | https://arxiv.org/abs/2109.05507

[105] A Complex Constrained Total Variation Image Denoising Algorithm with Application to Phase Retrieval作者 | Yunhui Gao, Liangcai Cao链接 | https://arxiv.org/abs/2109.05496 备注 | 11 pages, 7 figures

[106] Efficient Re-parameterization Residual Attention Network For Nonhomogeneous Image Dehazing作者 | Tian Ye, ErKang Chen, XinRui Huang, Peng Chen链接 | https://arxiv.org/abs/2109.05479

[107] CAN3D: Fast 3D Medical Image Segmentation via Compact Context Aggregation作者 | Wei Dai, Boyeong Woo, Siyu Liu, Matthew Marques, Craig B. Engstrom, Peter B. Greer, Stuart Crozier, Jason A. Dowling, Shekhar S. Chandras链接 | https://arxiv.org/abs/2109.05443 备注 | 21 pages, 7 figures

[108] Team NeuroPoly: Description of the Pipelines for the MICCAI 2021 MS New Lesions Segmentation Challenge作者 | Uzay Macar, Enamundram Naga Karthik, Charley Gros, Andréanne Lemay, Julien Cohen-Adad链接 | https://arxiv.org/abs/2109.05409 备注 | To be presented at the 2021 MICCAI Challenge on Multiple Sclerosis Lesion Segmentation (MSSEG-2); 8 pages in total

[109] Sickle Cell Disease Severity Prediction from Percoll Gradient Images using Graph Convolutional Networks作者 | Ario Sadafi, Asya Makhro, Leonid Livshits, Nassir Navab, Anna Bogdanova, Shadi Albarqouni, Carsten Marr链接 | https://arxiv.org/abs/2109.05372 备注 | Accepted for publication at MICCAI 2021 workshop on aFfordable healthcare and AI for Resource diverse global health (FAIR)

[110] Dual-view Snapshot Compressive Imaging via Optical Flow Aided Recurrent Neural Network作者 | Ruiying Lu, Bo Chen, Guanliang Liu, Ziheng Cheng, Mu Qiao, Xin Yuan链接 | https://arxiv.org/abs/2109.05287

[111] COSMic: A Coherence-Aware Generation Metric for Image Descriptions作者 | Mert İnan, Piyush Sharma, Baber Khalid, Radu Soricut, Matthew Stone, Malihe Alikhani链接 | https://arxiv.org/abs/2109.05281 备注 | 12 pages, 4 figures, Findings of the Association for Computational Linguistics: EMNLP 2021

[112] RVMDE: Radar Validated Monocular Depth Estimation for Robotics作者 | Muhamamd Ishfaq Hussain, Muhammad Aasim Rafique, Moongu Jeon链接 | https://arxiv.org/abs/2109.05265

[113] Follow the Curve: Robotic-Ultrasound Navigation with Learning Based Localization of Spinous Processes for Scoliosis Assessment作者 | Maria Victorova, Michael Ka-Shing Lee, David Navarro-Alarcon, Yongping Zheng链接 | https://arxiv.org/abs/2109.05196 备注 | Under Review in IEEE Robotics and Automation Letters (RA-L) with ICRA 2022

[114] Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label Correction作者 | Jiarun Liu, Ruirui Li, Chuan Sun链接 | https://arxiv.org/abs/2109.05159 备注 | IEEE Transactions on Medical Imaging 2021

[115] Medulloblastoma Tumor Classification using Deep Transfer Learning with Multi-Scale EfficientNets作者 | Marcel Bengs, Michael Bockmayr, Ulrich Schüller, Alexander Schlaefer链接 | https://arxiv.org/abs/2109.05025 备注 | Accepted at SPIE Medical Imaging 2021

[116] Real-time multimodal image registration with partial intraoperative point-set data作者 | Zachary M C Baum, Yipeng Hu, Dean C Barratt链接 | https://arxiv.org/abs/2109.05023 备注 | Accepted manuscript in Medical Image Analysis

[117] A Deep Learning-Based Unified Framework for Red Lesions Detection on Retinal Fundus Images作者 | Norah Asiri, Muhammad Hussain, Fadwa Al Adel, Hatim Aboalsamh链接 | https://arxiv.org/abs/2109.05021

机器学习/深度学习算法/自然语言处理交流群

已建立机器学习算-自然语言处理微信交流群！想要进交流群进行学习的同学，可以直接加我的微信号：HIT_NLP。加的时候备注一下：知乎+学校+昵称 （不加备注不会接受同意，望谅解），想进pytorch群，备注知乎+学校+昵称+Pytorch即可。然后我们就可以拉你进群了。群里已经有非得多国内外高校同学，交流氛围非常好。

强烈推荐大家关注机器学习算法与自然语言处理账号和机器学习算法与自然语言处理微信公众号，可以快速了解到最新优质的干货资源。

推荐阅读

ACL2021上的Dialogue

赛尔笔记 | 自然语言处理中模型的“偷懒”

ICLR2021 | 近期必读图神经网络精选论文 - 知乎 (zhihu.com)

AAAI 近20年最佳论文合集 - 知乎 (zhihu.com)

NAACL 2021 | 对比学习横扫文本聚类任务 - 知乎 (zhihu.com)

不可错过！CMU「概率图模型」课程，附Slides - 知乎 (zhihu.com)

ICCV 2021审稿结果出炉，有人已总结出了一份Rebuttal写作指南 - 知乎 (zhihu.com)

腾讯优图+厦门大学发布！2021十大人工智能趋势 - 知乎 (zhihu.com)

2021下半年会议论文投稿时间小结与历年接受率回顾（欢迎收藏） - 知乎 (zhihu.com)

赛尔笔记｜ 对话摘要简述 - 知乎 (zhihu.com)

PyTorch 常用代码段汇总 - 知乎 (zhihu.com)

Transformer长大了，它的兄弟姐妹们呢？（含Transformers超细节知识点） - 知乎 (zhihu.com)

Transformer Decoder-Only 模型批量生成 Trick - 知乎 (zhihu.com)

第十届全国社会媒体处理大会（SMP 2021） 技术评测方案 - 知乎 (zhihu.com)

首篇NLP图神经网络综述来了! 127页文档让你全面了解这个领域 - 知乎 (zhihu.com)

Transformer杀疯了！竟在图神经网络的ImageNet大赛中夺冠，力压DeepMind、百度...... - 知乎 (zhihu.com)

深度学习中的Attention总结 - 知乎 (zhihu.com)

【关于 AAAI 2021 之 情感分析论文串烧】那些你不知道的事 - 知乎 (zhihu.com)

ACL2021 main conference long papers list已出 - 知乎 (zhihu.com)

强烈推荐！斯坦福讲师出版《机器学习面试》书稿，涵盖200+考点！ - 知乎 (zhihu.com)

DeepMind科学家Trask著作《图解深度学习》，335页pdf与代码 - 知乎 (zhihu.com)

图自监督学习（Graph Self-supervised Learning）最新综述+Github代码汇总 - 知乎 (zhihu.com)

ICLR/CVPR时间更新 || 2021下半年会议论文投稿时间小结与历年接受率回顾（欢迎收藏） - 知乎 (zhihu.com)

每日论文速递：计算机视觉相关（6月29日更新版） - 知乎 (zhihu.com)

忆臻：每日论文速递：自然语言处理相关（6月29日更新版）

中科院软件所中文信息处理实验室招收2021年推免学生（硕博各2-3名） - 知乎 (zhihu.com)

一文掌握《对比学习（Contrastive Learning）》要旨，详述MoCo和SimCLR算法 - 知乎 (zhihu.com)

赛尔笔记|基于深度学习方法的对话状态跟踪综述 - 知乎 (zhihu.com)

近期必读的6篇顶会CVPR 2021【零样本学习（ZSL）】相关论文和代码 - 知乎 (zhihu.com)

计算机顶会论文投稿指南 - 知乎 (zhihu.com)

每日论文速递：计算机视觉相关（7月6日更新版） - 知乎 (zhihu.com)

每日论文速递：自然语言处理相关（7月6日更新版） - 知乎 (zhihu.com)

NTCIR-16 参与邀请 - 知乎 (zhihu.com)

十大NLP数据扩充策略 - 知乎 (zhihu.com)

一文速览 | ACL 2021 主会571篇长文分类汇总 - 知乎 (zhihu.com)

Hugging Face官方NLP课程来了！Transformers库维护者之一授课，完全免费 - 知乎 (zhihu.com)

ICML2021论文太多看不过来？这份《一句话点评1183篇论文亮点》帮你快速找到想看的 - 知乎 (zhihu.com)