Description
FCOS is an anchor-box free, proposal free, single-stage object detection model. By eliminating the predefined set of anchor boxes, FCOS avoids computation related to anchor boxes such as calculating overlapping during training. It also avoids all hyper-parameters related to anchor boxes, which are often very sensitive to the final detection performance.
Papers Using This Method
Floating Car Observers in Intelligent Transportation Systems: Detection Modeling and Temporal Insights2025-04-29BBoxCut: A Targeted Data Augmentation Technique for Enhancing Wheat Head Detection Under Occlusions2025-03-31Fast-COS: A Fast One-Stage Object Detector Based on Reparameterized Attention Vision Transformer for Autonomous Driving2025-02-11Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection2024-12-23IAFI-FCOS: Intra- and across-layer feature interaction FCOS model for lesion detection of CT images2024-09-01Domain penalisation for improved Out-of-Distribution Generalisation2024-08-03Enhancing Fine-grained Object Detection in Aerial Images via Orthogonal Mapping2024-07-25FAD-SAR: A Novel Fishing Activity Detection System via Synthetic Aperture Radar Images Based on Deep Learning Method2024-04-28Temporal Enhanced Floating Car Observers2024-03-06Performance Evaluation of Semi-supervised Learning Frameworks for Multi-Class Weed Detection2024-03-06A Safety-Adapted Loss for Pedestrian Detection in Automated Driving2024-02-05Mixed Pseudo Labels for Semi-Supervised Object Detection2023-12-12DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors2023-11-28P2RBox: Point Prompt Oriented Object Detection with SAM2023-11-22HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information2023-10-07Recognizing Handwritten Mathematical Expressions of Vertical Addition and Subtraction2023-08-10AlignDet: Aligning Pre-training and Fine-tuning in Object Detection2023-07-20Training Strategies for Vision Transformers for Object Detection2023-04-05EdgeYOLO: An Edge-Real-Time Object Detector2023-02-15Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images2023-02-13