arXiv (Cornell University) · 2019 · 802 citations · 25 references
ComputingComputer EngineeringComputer ScienceComputer VisionEarly DetectionMachine VisionObject DetectionObject RecognitionSemantic SegmentationVisual DetectionAccuracyAnchor-free DetectionFully Convolutional NetworksNon-maximum SuppressionOne-stage Detectors
Almost all state‑of‑the‑art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R‑CNN rely on pre‑defined anchor boxes. The authors propose FCOS, a fully convolutional one‑stage detector that performs per‑pixel object detection analogous to semantic segmentation. FCOS is anchor‑ and proposal‑free, eliminating anchor‑related computations and hyper‑parameters, thereby simplifying training. FCOS, using ResNeXt‑64x4d‑101 and only NMS, attains 44.7% AP on single‑model, single‑scale testing, surpassing prior one‑stage detectors while offering a simpler, more accurate framework. Code is available at https://tinyurl.com/FCOSv1.
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 pre-defined 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: https://tinyurl.com/FCOSv1.
25
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 61.8K citations
Fully convolutional networks for semantic segmentation
Jonathan Long, Evan Shelhamer, Trevor Darrell · 2015 · 36.9K citations
Feature Pyramid Networks for Object Detection
Tsung-Yi Lin, Piotr Dollár, Ross Girshick et al. · 2017 · 28.7K citations