GT CV

- Uncertainty Estimation Using a Single Deep Deterministic Neural Network. Joost van Amersfoort, Lewis Smith, Yee Whye Teh, Yarin Gal. ICML 2020. [arXiv]
- Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness. Jeremiah Zhe Liu, Zi Lin, Shreyas Padhy, Dustin Tran, Tania Bedrax-Weiss, Balaji Lakshminarayanan. arXiv preprint. [arXiv]
- Density of States Estimation for Out-of-Distribution Detection. Warren R. Morningstar, Cusuh Ham, Andrew G. Gallagher, Balaji Lakshminarayanan, Alexander A. Alemi, Joshua V. Dillon. arXiv preprint. [arXiv]
- The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization. Dan Hendrycks, Steven Basart*, Norman Mu*, Saurav Kadavath, Frank Wang, Evan Dorundo, Rahul Desai, Tyler Zhu, Samyak Parajuli, Mike Guo, Dawn Song, Jacob Steinhardt, Justin Gilmer. arXiv preprint. [arXiv]

- MONet: Unsupervised Scene Decomposition and Representation. Christopher P. Burgess, Loic Matthey, Nicholas Watters, Rishabh Kabra, Irina Higgins, Matt Botvinick, Alexander Lerchner. arXiv preprint. [arXiv]
- Multi-Object Representation Learning with Iterative Variational Inference. Klaus Greff, Raphael Lopez Kaufman, Rishabh Kabra, Nick Watters, Chris Burgess, Daniel Zoran, Loic Matthey, Matthew Botvinick, Alexander Lerchner. ICML 2019. [arXiv]

- Stacked Cross Attention for Image-Text Matching. Kuang-Huei Lee, Xi Chen, Gang Hua, Houdong Hu, Xiaodong He. ECCV 2018. [arXiv]
- CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval. Zihao Wang*, Xihui Liu*, Hongsheng Li, Lu Sheng, Junjie Yan, Xiaogang Wang, Jing Shao. ICCV 2019. [arXiv]
- Context-Aware Attention Network for Image-Text Retrieval. Qi Zhang, Zhen Lei, Zhaoxiang Zhang, Stan Z. Li. CVPR 2020. [paper]

- VirTex: Learning Visual Representations from Textual Annotations. Karan Desai, Justin Johnson. arXiv preprint. [arXiv]
- Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision. Hao Tan, Mohit Bansal. EMNLP 2020. [arXiv]

- Explainable AI: Beware of Inmates Running the Asylum. Tim Miller, Piers Howe, Liz Sonenberg. IJCAI 2017 Workshop on Explainable AI. [arXiv]
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra. ICCV 2017. [arXiv]
- Explaining Explanations: An Overview of Interpretability of Machine Learning. Leilani H. Gilpin, David Bau, Ben Z. Yuan, Ayesha Bajwa, Michael Specter, Lalana Kagal. DSAA 2018. [arXiv]

- Momentum Contrast for Unsupervised Visual Representation Learning. Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick. arXiv preprint. [arXiv]
- Self-Supervised Learning of Pretext-Invariant Representations. Ishan Misra, Laurens van der Maaten. CVPR 2020. [arXiv]
- A Simple Framework for Constrastive Learning of Visual Representations. Ting Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey Hinton. arXiv preprint. [arXiv]

- Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters. Axel Barroso-Laguna, Edgar Riba, Daniel Ponsa, Krystian Mikolajczyk. ICCV 2019. [arXiv]
- GLAMpoints: Greedily Learned Accurate Match points. Prune Truong, Stefanos Apostolopoulos, Agata Mosinska, Samuel Stucky, Carlos Ciller. ICCV 2019. [arXiv]

- SuperPoint: Self-Supervised Interest Point Detection and Description. Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich. CVPR 2018. [arXiv]
- D2-Net: A Trainable CNN for Joint Description and Detection of Local Features. Mihai Dusmanu, Ignacio Rocco, Tomas Pajdla, Marc Pollefeys, Josef Sivic, Akihiko Torii, Torsten Sattler. CVPR 2019. [arXiv]

- Universal Correspondence Network. Christopher B. Choy, JunYoung Gwak, Silvio Savarese, Manmohan Chandraker. NeurIPS 2016. [arXiv]

- Learning to Find Good Correspondences. Kwang Moo Yi*, Eduard Trulls*, Yuki Ono, Vincent Lepetit, Mathieu Salzmann, Pascal Fua. CVPR 2018. [arXiv]
- Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses. Zheng Dang, Kwang Moo Yi, Yinlin Hu, Fei Wang, Pascal Fua, Mathieu Salzmann. ECCV 2018. [arXiv]
- Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses. Eric Brachmann, Carsten Rother. ICCV 2019. [arXiv]

- Do Deep Generative Models Know What They Don't Know?. Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh, Dilan Gorur, Balaji Lakshminarayanan. ICLR 2019. [arXiv]
- Likelihood Ratios for Out-of-Distribution Detection. Jie Ren, Peter J. Liu, Emily Fertig, Jasper Snoek, Ryan Poplin, Mark A. DePristo, Joshua V. Dillon, Balaji Lakshminarayanan. NeurIPS 2019. [arXiv]
- Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality. Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh, Balaji Lakshminarayanan. NeurIPS Workshop on Bayesian Deep Learning 2019. [arXiv]
- Reducing Network Agnostophobia. Akshay Raj Dhamija, Manuel Günther, Terrance E. Boult. NeurIPS 2018. [arXiv]

- Panoptic Segmentation. Alexander Kirillov, Kaiming He, Ross Girshick, Carsten Rother, Piotr Dollár. CVPR 2019. [paper]
- Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving. Yan Wang, Wei-Lun Chao, Divyansh Garg, Bharath Hariharan, Mark Campbell, Kilian Q. Weinberger. CVPR 2019. [paper]
- Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression. Hamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian Reid, Silvio Savarese. CVPR 2019. [paper]
- End-to-end Interpretable Neural Motion Planner. Wenyuan Zeng, Wenjie Luo, Simon Suo, Abbas Sadat, Bin Yang, Sergio Casas, Raquel Urtasun. CVPR 2019. [paper]
- Deep Rigid Instance Scene Flow. Wei-Chiu Ma, Shenlong Wang, Rui Hu, Yuxen Xiong, Raquel Urtasun. CVPR 2019. [paper]
- Argoverse: 3D Tracking and Forecasting with Rich Maps. Ming-Fang Chang*, John Lambert*, Patsorn Sangkloy*, Jagjeet Singh*, Slawomir Bak, Andrew Hartnett, De Wang, Peter Carr, Simon Lucey, Deva Ramanan, James Hays. CVPR 2019. [paper] - D2-Net: A Trainable CNN for Joint Description and Detection of Local Features. Mihai Dusmanu, Ignacio Rocco, Tomas Pajdla, Marc Pollefeys, Josef Sivic, Akihiko Torii, Torsten Sattler. CVPR 2019. [paper]

- 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. Christopher Choy, JunYoung Gwak, Silvio Savarese. CVPR 2019. [paper]
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation. Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, Steven Lovegrove. CVPR 2019. [arXiv]
- Occupancy Networks: Learning 3D Reconstruction in Function Space. Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, Andreas Geiger. CVPR 2019. [arXiv]
- Pushing the Boundaries of View Extrapolation with Multiplane Images. Pratul P. Srinivasan, Richard Tucker, Jonathan T. Barron. CVPR 2019. [arXiv]
- DeepVoxels: Learning Persistent 3D Feature Embeddings. Vincent Sitzmann, Justus Thies, Felix Heide, Matthias Nießner, Gordon Wetzstein, Michael Zollhöfer. CVPR 2019. [arXiv]
- Strand-accurate Multi-view Hair Capture. Giljoo Nam, Chenglei Wu, Min H. Kim, Yaser Sheikh. CVPR 2019. [paper]

- A Style-Based Generator Architecture for Generative Adversarial Networks. Tero Karras, Samuli Laine, Timo Aila. CVPR 2019. [arXiv]
- Semantic Image Synthesis with Spatially-Adaptive Normalization. Taesung Park, Ming-Yu Liu, Ting-Chun Wang, Jun-Yan Zhu. CVPR 2019. [arXiv]
- Shapes and Context: In-the-Wild Image Synthesis & Manipulation. Aayush Bansal, Yaser Sheikh, Deva Ramanan. CVPR 2019. [arXiv]
- Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors. Yedid Hoshen, Jitendra Malik. CVPR 2019. [arXiv]
- Conditional Adversarial Generative Flow for Controllable Image Synthesis. Rui Liu, Yu Liu, Xinyu Gong, Xiaogang Wang, Hongsheng Li. CVPR 2019. [arXiv]
- Unsupervised Primitive Discovery for Improved 3D Generative Modeling. Salman H. Khan, Yulan Guo, Munawar Hayat, Nick Barnes. CVPR 2019. [paper]

- Tracking without bells and whistles. Philipp Bergmann*, Tim Meinhardt*, Laura Leal-Taixe. arXiv pre-print 2019. [arXiv]
- Heterogeneous Association Graph Fusion for Target Association in Multiple Object Tracking. Hao Sheng, Yang Zhang, Jiahui Chen, Zhang Xiong, Jun Zhang. TCSVT 2018. [paper]
- Improvements to Frank-Wolfe optimization for multi-detector multi-object tracking. Roberto Henschel, Laura Leal-Taixe, Daniel Cremers, Bodo Rosenhahn. arXiv pre-print 2017. [arXiv]
- Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering. Margret Keuper, Siyu Tang, Bjoern ANdres, Thomas Brox, Bernt Schiele. PAMI 2018. [paper]
- Real-Time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-identification. Long Chen, Haizhou Ai, Zijie Zhuang, Chong Shang. ICME 2018. [arXiv]
- Multiple Hypothesis Tracking Revisited. Chanho Kim, Fuxin Li, Arridhana Ciptadi, James M. Rehg. ICCV 2016. [paper]

- Modeling Uncertainty with Hedged Instance Embedding. Seong Joon Oh, Kevin Murphy, Jiyan Pan, Joseph Roth, Florian Schroff, Andrew Gallagher. ICLR 2019. [arXiv]
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? Alex Kendall, Yarin Gal. NeurIPS 2017. [arXiv]
- Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. Yarin Gal, Zoubin Ghahramani. ICML 2016. [arXiv]

- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun. NeurIPS 2015. [arXiv]
- Feature Pyramid Networks for Object Detection. Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie. CVPR 2017. [arXiv]
- Focal Loss for Dense Object Detection. Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, Piotr Dollár. ICCV 2017. [arXiv]

- SSD: Single Shot MultiBox Detector. Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg. ECCV 2016. [arXiv]
- YOLO9000: Better, Faster, Stronger. Joseph Redmon, Ali Farhadi. CVPR 2017. [arXiv]
- YOLOv3: An Incremental Improvement. Joseph Redmon, Ali Farhadi. arXiv pre-print. [arXiv]

- Fully Convolutional Instance-aware Semantic Segmentation. Yi Li*, Haozhi Qi*, Jifeng Dai, Xiangyang Ji, Yichen Wei. CVPR 2017. [arXiv]
- Mask R-CNN. Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick. ICCV 2017. [arXiv]
- Mask Scoring R-CNN. Zhaojin Huang, Lichao Huang, Yongchao Gong, Chang Huang, Xinggang Wang. CVPR 2019. [arXiv]

- YOLACT: Real-Time Instance Segmentation. Daniel Bolya, Chong Zhou, Fanyi Xiao, Yong Jae Lee. ICCV 2019. [arXiv]

- Texture Fields: Learning Texture Representations in Function Space. Michael Oechsle, Lars Mescheder, Michael Niemeyer, Thilo Strauss, Andreas Geiger. ICCV 2019. [paper] - PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothes Human Digitization. Shunsuke Saito*, Zeng Huang*, Ryota Natsume*, Shigeo Morishima, Angjoo Kanazawa, Hao Li. ICCV 2019. [arXiv]

- Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics. Michael Niemeyer, Lars Mescheder, Michael Oechsle, Andreas Geiger. ICCV 2019. [paper]

- Occupancy Networks: Learning 3D Reconstruction in Function Space. Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, Andreas Geiger. CVPR 2019. [arXiv] - DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation. Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, Steven Lovegrove. CVPR 2019. [arXiv]

Understanding how humans and machines learn from few examples remains a fundamental challenge. Humans are remarkably able to grasp a new concept from just few examples, or learn a new skill from just few trials. By contrast, state-of-the-art machine learning techniques typically require thousands of training examples and often break down if the training sample set is too small. In this talk, I will discuss our efforts towards endowing visual learning systems with few-shot learning ability. Our key insight is that the visual world is well structured and highly predictable not only in feature spaces but also in under-explored model and data spaces. Such structures and regularities enable the systems to learn how to learn new tasks rapidly by reusing previous experiences. I will focus on a few topics to demonstrate how to leverage this idea of learning to learn, or meta-learning, to address a broad range of few-shot learning tasks: meta-learning in model space and task-oriented generative modeling. I will also discuss some ongoing work towards building machines that are able to operate in highly dynamic and open environments, making intelligent and independent decisions based on insufficient information.

Yuxiong Wang is a postdoctoral fellow in the Robotics Institute at Carnegie Mellon University. He received a Ph.D. in robotics in 2018 from Carnegie Mellon University. His research interests lie in the intersection of computer vision, machine learning, and robotics, with a particular focus on few-shot learning and meta-learning. He has spent time at Facebook AI Research (FAIR).