FCOS: A simple and strong anchor-free object detector
arXiv:2006.09214
Abstract
In computer vision, object detection is one of most important tasks, which underpins a few instance-level recognition tasks and many downstream applications. Recently one-stage methods have gained much attention over two-stage approaches due to their simpler design and competitive performance. Here we propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to other dense prediction problems such as 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 pre-defined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating the intersection over union (IoU) scores during training. More importantly, we also avoid all hyper-parameters related to anchor boxes, which are often sensitive to the final detection performance. With the only post-processing non-maximum suppression (NMS), 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 and pre-trained models are available at: https://git.io/AdelaiDet
arXiv commentAccepted to IEEE Transactions on Pattern Analysis and Machine Intelligence. Extended version of arXiv:1904.01355; Code is at: https://git.io/AdelaiDet
References in corpus (9)
- 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
- CrowdHuman: A Benchmark for Detecting Human in a Crowd
- DenseBox: Unifying Landmark Localization with End to End Object Detection
- Beyond Skip Connections: Top-Down Modulation for Object Detection
- AutoAssign: Differentiable Label Assignment for Dense Object Detection
- DirectPose: Direct End-to-End Multi-Person Pose Estimation