- Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection IROS 2019
- PointPillars: Fast Encoders for Object Detection from Point Clouds CVPR 2019, nuTonomy / APTIV
- LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving CVPR 2019, Uber ATG
- Frustum PointNets for 3D Object Detection from RGB-D Data CVPR 2018, link
- PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation CVPR 2018, stanford University & Zoox
- PIXOR: Real-time 3D Object Detection from Point Clouds CVPR 2018, Uber ATG / Uni Toronto code
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection CVPR 2018, Apple
- Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net CVPR 2018, Uber
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation CVPR 2017, Stanford University code
- Multi-Task Multi-Sensor Fusion for 3D Object Detection, CVPR 2019, Uber / University of Toronto
- Multi-View 3D Object Detection Network for Autonomous Driving CVPR 2017, Baidu
- End-to-end Lane Detection through Differentiable Least-Squares Fitting ArXiv preprint 2019, KU Leuven code
- FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network CVPR 2019
- Multiple Encoder-Decoders Net for Lane Detection ICLR 2019
- Towards End-to-End Lane Detection: an Instance Segmentation Approach IEEE IV 2018, KU Leuven code
- Spatial As Deep: Spatial CNN for Traffic Scene Understanding IAAA 2018, The Chinese University of Hong Kong code data set
- Deep Multi-Sensor Lane Detection IROS 2018, Uber ATG / Uni Toronto
- LaneNet: Real-Time Lane Detection Networks for Autonomous Driving Horizon Robotics & Duke University
- 3D-LaneNet: end-to-end 3D multiple lane detection 2018, General Motors
- A Dataset for Lane Instance Segmentation in Urban Environments ECCV 2018, FiveAI
- EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection CoRR 2018, TomTom
- Deep Semantic Lane Segmentation for Mapless Driving IROS 2018, FZI / KIT Karlsruhe
- MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving CoRR 2018, University Toronto / Uber
- VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition CVPR 2017, KAIST, Samsung code
- End-to-End Ego Lane Estimation based on Sequential Transfer Learning for Self-Driving Cars CVPR workshop 2017, Samsung
- Efficient Deep Models for Monocular Road Segmentation IROS 2016, University of Freiburg
- DeepLanes: End-To-End Lane Position Estimation using Deep Neural Networks CVPR workshop 2016, Ford Research
- An Empirical Evaluation of Deep Learning on Highway Driving CoRR 2015, Stanford University, Baidu Research
- CULane Multimedia Laboratory, The Chinese University of Hong Kong
- TuSimple TuSimple, highway driving only demo challenge
- A Dataset for Lane Instance Segmentation in Urban Environments FIVE AI
- Berkeley Deep Drive BDD100K: A Large-scale Diverse Driving Video Database paper
- Lyft Level 5 AV Dataset 2019 devkit
- nuScenes: A multimodal dataset for autonomous driving nuScenes, 2019 link
- Semantic KITTI A Dataset for Semantic Scene Understanding using LiDAR Sequences
- A Dataset for Semantic Segmentation of Point Cloud Sequences ICCV 2019, University of Bonn GitHub link
- Mapillary Vistas Dataset ICCV 2017 paper
- Fast Scene Understanding for Autonomous Driving IV 2017
- Semantic Instance Segmentation with a Discriminative Loss Function CoRR 2017 code
- ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation CoRR 2016
- High-Performance Large-Scale Image Recognition Without Normalization DeepMind 2021 code
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks ICML 2019 code
- Benchmark Analysis of Representative Deep Neural Network Architectures
- Xception: Deep Learning with Depthwise Separable Convolutions CVPR 2017, Google
- Pyramid Scene Parsing Network CVPR 2017
- An Analysis of Deep Neural Network Models for Practical Applications ICLR 2017
- Multigrid Neural Architectures CVPR 2016
- Deep Residual Learning for Image Recognition ResNet, CVPR 2016
- Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences NIPS 2016 code
- Spatial Transformer Networks NIPS 2015, Google DeepMind
- Highway Networks ICML DL Workshop 2015
- On the difficulty of training Recurrent Neural Networks ICML 2013
- LONG SHORT-TERM MEMORY 1997
- Understanding the Disharmony between Dropout and Batch Normalization by Variance Shift CVPR 2019
- Benchmarking Neural Network Robustness to Common Corruptions and Perturbations ICLR 2019
- Exploring the Limits of Weakly Supervised Pretraining arXiv 2018, Facebook
- Quantizing deep convolutional networks for efficient inference: A whitepaper Google
- Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference CVPR 2018, Google
- [https://arxiv.org/abs/1503.02531v1](Distilling the Knowledge in a Neural Network) Google 2015
- [https://arxiv.org/abs/1505.04467](Exploring Nearest Neighbor Approaches for Image Captioning) 2015
- Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Nature 2020, DeepMind
- Strong-Weak Distribution Alignment for Adaptive Object Detection CVPR 2019, Boston University
- Domain Adaptive Faster R-CNN for Object Detection in the Wild CVPR 2018, ETH
- Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks? ICRA 2017, University of Michigan
- Unsupervised Domain Adaptation by Backpropagation ICML 2015
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation ECCV 2018, Google
- TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation TechReport 2018
- ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation IEEE T-ITS 2017
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation PAMI 2017, University of Cambridge
- ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation ArXiv preprint 2016
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs ArXiv preprint 2016
- Fully Convolutional Networks for Semantic Segmentation FCN architecture, PAMI 2016
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs ICLR 2015
- Fully Convolutional Networks for Semantic Segmentation FCN architecture, CVPR 2015
- U-Net: Convolutional Networks for Biomedical Image Segmentation MICCAI 2015, University of Freiburg, link
- Learning Deconvolution Network for Semantic Segmentation ICCV 2015
- Feature Pyramid Networks for Object Detection CVPR 2017
- Speed/accuracy trade-offs for modern convolutional object detectors CVPR 2017
- SSD: Single Shot MultiBox Detector SSD, ECCV 2016
- You Only Look Once: Unified, Real-Time Object Detection YOLO, CVPR 2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Faster R-CNN, NIPS 2015
- Fast R-CNN Fast R-CNN, ICCV 2015
- Rich feature hierarchies for accurate object detection and semantic segmentation R-CNN, CVPR 2014
- Selective Search for Object Recognition IJCV 2013
- How Do Neural Networks See Depth in Single Images? ICCV 2019, TU Delft
- Learning Depth from Monocular Videos using Direct Methods CVPR 2018, CMU
- Unsupervised Monocular Depth Estimation with Left-Right Consistency CVPR 2017, University College London
- Unsupervised Learning of Depth and Ego-Motion from Video CVPR 2017, UC Berkeley & Google project webpage
- Semi-Supervised Deep Learning for Monocular Depth Map Prediction CVPR 2017, RWTH Aachen
- Deep Single Image Camera Calibration with Radial Distortion CVPR 2019, Mapillary
- A Perceptual Measure for Deep Single Image Camera Calibration CVPR 2018, Adobe
- Convolutional Recurrent Network for Road Boundary Extraction CVPR 2019, Uber / University of Toronto / MIT
- Social LSTM: Human Trajectory Prediction in Crowded Spaces CVPR 2016, University of Stanford
- Convolutional Social Pooling for Vehicle Trajectory Prediction CVPRW 2018, University of California, San Diego
- Bundle Adjustment — A Modern Synthesis survey, ICCV 1999
- Visualizing Data using t-SNE