深度学习论文

目标检测

• YOLOX: Exceeding YOLO Series in 2021
• Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
• Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection
• FCOS: Fully Convolutional One-Stage Object Detection
• Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
• EfficientDet: Scalable and Efficient Object Detection
• Objects as Points
• End-to-End Object Detection with Transformers
• Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation

实例分割

• SOLO: Segmenting Objects by Locations
• SOLOv2: Dynamic and Fast Instance Segmentation
• YOLACT Real-time Instance Segmentation
• YOLACT++ Better Real-time Instance Segmentation
• Path Aggregation Network for Instance Segmentation
• Conditional Convolutions for Instance Segmentation
• CenterMask : Real-Time Anchor-Free Instance Segmentation
• Mask Encoding for Single Shot Instance Segmentation
• BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation

语义分割

• Fast-SCNN: Fast Semantic Segmentation Network
• BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
• ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
• ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
• Dual Attention Network for Scene Segmentation
• Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes
• LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation
• Panoptic Feature Pyramid Networks
• Context Encoding for Semantic Segmentation

车道线检测

• Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes
• YOLOP: You Only Look Once for Panoptic Driving Perception
• HybridNets: End-to-End Perception Network
• CLRNet Cross Layer Refinement Network for Lane Detection
• Ultra Fast Structure-aware Deep Lane Detection
• Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection
• CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution
• LaneNet: Real-Time Lane Detection Networks for Autonomous Driving
• A Keypoint-based Global Association Network for Lane Detection
• Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networks
• Key Points Estimation and Point Instance Segmentation Approach for Lane Detection
• Towards End-to-End Lane Detection: an Instance Segmentation Approach
• Spatial As Deep: Spatial CNN for Traffic Scene Understanding
• Learning Lightweight Lane Detection CNNs by Self Attention Distillation
• Robust Lane Detection via Expanded Self Attention
• Enhanced free space detection in multiple lanes based on single CNN with scene identification
• Lane Detection and Classification using Cascaded CNNs
• RESA: Recurrent Feature-Shift Aggregator for Lane Detection
• PolyLaneNet: Lane Estimation via Deep Polynomial Regression
• Rethinking Efficient Lane Detection via Curve Modeling
• Line-CNN:End-to-End Traffic Line Detection With Line Proposal Unit
• Lane Detection Model Based on Spatio-Temporal Network With Double Convolutional Gated Recurrent Units
• Lane Detection in Low-light Conditions Using an Efficient Data Enhancement : Light Conditions Style Transfer
• LaneAF: Robust Multi-Lane Detection with Affinity Fields
• End-to-End Lane Marker Detection via Row-wise Classification
• End-to-end Lane Detection through Differentiable Least-Squares Fitting
• Structure Guided Lane Detection