FCOS: Fully Convolutional One-Stage Object Detection
arXiv:1904.01355
Abstract
We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely on pre-defined anchor boxes. In contrast, our proposed detector FCOS is anchor box free, as well as proposal free. By eliminating the predefined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating overlapping during training. More importantly, we also avoid all hyper-parameters related to anchor boxes, which are often very sensitive to the final detection performance. With the only post-processing non-maximum suppression (NMS), FCOS with ResNeXt-64x4d-101 achieves 44.7% in AP with single-model and single-scale testing, surpassing previous one-stage detectors with the advantage of being much simpler. For the first time, we demonstrate a much simpler and flexible detection framework achieving improved detection accuracy. We hope that the proposed FCOS framework can serve as a simple and strong alternative for many other instance-level tasks. Code is available at:Code is available at: https://tinyurl.com/FCOSv1
Accepted to Proc. Int. Conf. Computer Vision 2019. 13 pages. Code is available at: https://github.com/tianzhi0549/FCOS/
References in corpus (7)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- YOLOv3: An Incremental Improvement
- DSSD : Deconvolutional Single Shot Detector
- Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
- DenseBox: Unifying Landmark Localization with End to End Object Detection
- Beyond Skip Connections: Top-Down Modulation for Object Detection
- Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
Cited by in corpus (77)
- A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS
- MMDetection: Open MMLab Detection Toolbox and Benchmark
- Deep High-Resolution Representation Learning for Visual Recognition
- Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
- A Dataset And Benchmark Of Underwater Object Detection For Robot Picking
- DeepSOCIAL: Social Distancing Monitoring and Infection Risk Assessment in COVID-19 Pandemic
- DirectPose: Direct End-to-End Multi-Person Pose Estimation
- Revisiting Feature Alignment for One-stage Object Detection
- PolarMask: Single Shot Instance Segmentation with Polar Representation
- SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines
- SOLQ: Segmenting Objects by Learning Queries
- RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving
- RS-YOLOX: A High Precision Detector for Object Detection in Satellite Remote Sensing Images
- Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection
- SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking
- QueryProp: Object Query Propagation for High-Performance Video Object Detection
- RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
- CPS++: Improving Class-level 6D Pose and Shape Estimation From Monocular Images With Self-Supervised Learning
- Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies
- CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection
- FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network
- DSGN: Deep Stereo Geometry Network for 3D Object Detection
- NAS-FCOS: Fast Neural Architecture Search for Object Detection
- Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots
- Empirical Upper Bound in Object Detection and More
- Dense Label Encoding for Boundary Discontinuity Free Rotation Detection
- TOOD: Task-aligned One-stage Object Detection
- HRDNet: High-resolution Detection Network for Small Objects
- BorderDet: Border Feature for Dense Object Detection
- RetinaTrack: Online Single Stage Joint Detection and Tracking
- AD-Det: Boosting Object Detection in UAV Images with Focused Small Objects and Balanced Tail Classes
- Control Distance IoU and Control Distance IoU Loss Function for Better Bounding Box Regression
- MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection
- TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model
- IoU-uniform R-CNN: Breaking Through the Limitations of RPN
- Self-Supervised 3D Keypoint Learning for Ego-motion Estimation
- NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection
- Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax
- Multi-Scale Feature Aggregation by Cross-Scale Pixel-to-Region Relation Operation for Semantic Segmentation
- BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansion
- Can we cover navigational perception needs of the visually impaired by panoptic segmentation?
- Towards large-scale, automated, accurate detection of CCTV camera objects using computer vision. Applications and implications for privacy, safety, and cybersecurity. (Preprint)
- A unified neural network for object detection, multiple object tracking and vehicle re-identification
- 1st Place Solution for ICDAR 2021 Competition on Mathematical Formula Detection
- Learning from Noisy Anchors for One-stage Object Detection
- Seesaw Loss for Long-Tailed Instance Segmentation
- iffDetector: Inference-aware Feature Filtering for Object Detection
- Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search
- Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection
- Improvement of Classification in One-Stage Detector
- MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection
- Instance and Panoptic Segmentation Using Conditional Convolutions
- IQDet: Instance-wise Quality Distribution Sampling for Object Detection
- Multiple Anchor Learning for Visual Object Detection
- AFO-TAD: Anchor-free One-Stage Detector for Temporal Action Detection
- Reducing Label Noise in Anchor-Free Object Detection
- Representation Sharing for Fast Object Detector Search and Beyond
- A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
- Real-Time Panoptic Segmentation from Dense Detections
- Progressive Hard-case Mining across Pyramid Levels for Object Detection
- Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections
- Scale Match for Tiny Person Detection
- Detecting Out-of-distribution Objects Using Neuron Activation Patterns
- LGA-RCNN: Loss-Guided Attention for Object Detection
- An Autonomous Approach to Measure Social Distances and Hygienic Practices during COVID-19 Pandemic in Public Open Spaces
- Scope Head for Accurate Localization in Object Detection
- Visible Feature Guidance for Crowd Pedestrian Detection
- Understanding in Artificial Intelligence
- Quality-Aware Network for Face Parsing
- DSIC: Dynamic Sample-Individualized Connector for Multi-Scale Object Detection
- Perceiving Traffic from Aerial Images
- Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaboration
- Bootstrap Your Object Detector via Mixed Training
- Contrast R-CNN for Continual Learning in Object Detection
- ContourRender: Detecting Arbitrary Contour Shape For Instance Segmentation In One Pass
- Smart Black Box 2.0: Efficient High-bandwidth Driving Data Collection based on Video Anomalies
- Empirical Upper Bound, Error Diagnosis and Invariance Analysis of Modern Object Detectors