Objects as Points
Explore this paper's citation graph
Summary
The center point based approach, CenterNet, is end-to-end differentiable, simpler, faster, and more accurate than corresponding bounding box based detectors and performs competitively with sophisticated multi-stage methods and runs in real-time.
- Type
- preprint
- Published
- 2019-04-16
- Cited by
- 3,801
- References
- 64
- Access
- Open access
- OpenAlex
- https://openalex.org/W2935837427
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:118714035
Keywords
Minimum bounding box, Benchmark (surveying), Computer science, Bounding overwatch, Orientation (vector space)
References
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- You Only Look Once: Unified, Real-Time Object Detection
- Fully convolutional networks for semantic segmentation
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- DeepPose: Human Pose Estimation via Deep Neural Networks
- Tracking-Learning-Detection
- Are we ready for autonomous driving? The KITTI vision benchmark suite
- 3D Object Proposals for Accurate Object Class Detection
- Deep Residual Learning for Image Recognition
- Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- Monocular 3D Object Detection for Autonomous Driving
- Aggregated Residual Transformations for Deep Neural Networks
- Fully Convolutional Instance-Aware Semantic Segmentation
- Associative Embedding: End-to-End Learning for Joint Detection and Grouping
- Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors
- Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
- 3D Bounding Box Estimation Using Deep Learning and Geometry
- VQA: Visual Question Answering
Cited by
- Dual Refinement Network for Single-Shot Object Detection
- FoveaBox: Beyound Anchor-Based Object Detection
- CenterNet: Keypoint Triplets for Object Detection
- Object Detection in 20 Years: A Survey
- Double-Head RCNN: Rethinking Classification and Localization for Object Detection
- Revisiting Feature Alignment for One-stage Object Detection
- Mask Point R-CNN
- Object detection on aerial imagery using CenterNet
- Residual Objectness for Imbalance Reduction
- DEBUG: A Dense Bottom-Up Grounding Approach for Natural Language Video Localization
- A Survey of Deep Learning-Based Object Detection
- Training-Time-Friendly Network for Real-Time Object Detection
- Are Sampling Heuristics Necessary in Object Detectors?
- Pose Neural Fabrics Search
- Pixel-Level Dense Prediction without Decoder
- DeepMark: One-Shot Clothing Detection
- SNIDER: Single Noisy Image Denoising and Rectification for Improving License Plate Recognition
- CSID: Center, Scale, Identity and Density-aware Pedestrian Detection in a Crowd
- Modular Lightweight Network for Road Object Detection Using a Feature Fusion Approach
- Identification of primary angle-closure on AS-OCT images with Convolutional Neural Networks