You Only Look One-level Feature

By Qiang Chen, Yingming Wang, Tong Yang, X. Zhang, Jian Cheng, Jian‐Yuan Sun. 2021

683 citations recorded by the source corpus.

This paper revisits feature pyramids networks (FPN) for one-stage detectors and points out that the success of FPN is due to its divide-and-conquer solution to the optimization problem in object detection rather than multi-scale feature fusion. From the perspective of optimization, we introduce an alternative way to address the problem instead of adopting the complex feature pyramids - utilizing only one-level feature for detection. Based on the simple and efficient solution, we present You Only Look One-level Feature (YOLOF). In our method, two key components, Dilated Encoder and Uniform Matching, are proposed and bring considerable improvements. Extensive experiments on the COCO benchmark prove the effectiveness of the proposed model. Our YOLOF achieves comparable results with its feature pyramids counterpart RetinaNet while being 2.5× faster. Without transformer layers, YOLOF can match the performance of DETR in a single-level feature manner with 7× less training epochs. Code is available at https://github.com/megvii-model/YOLOF.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Exploring Plain Vision Transformer Backbones for Object Detection (2022, background): “More recently, works including Trident Networks [33] and YOLOF [7] have revisited single-scale feature maps, but unlike our work they focus on a single-scale taken from a hierarchical backbone.”
YOLOX: Exceeding YOLO Series in 2021 (2021, methodology): “It is then widely used in YOLOv4 [1], YOLOv5 [7] and other detectors [3].”
MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression (2023, methodology): “, YOLO series [1, 2, 3, 4, 5, 6], Mask R-CNN [7], Dynamic R-CNN [8] and DETR [9]) rely on a bounding box regression (BBR) module to determine the position of objects.”
Anchor DETR: Query Design for Transformer-Based Detector (2022, background): “In the last decades, there are many great progresses in object detection based on the CNN (Ren et al. 2015; Cai and Vasconcelos 2018; Redmon et al. 2016; Lin et al. 2017; Zhang et al. 2019; Qiao, Chen, and Yuille 2020; Chen et al. 2021).”
Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism (2023, neutral): “YOLO-F [6] achieved state-of-the-art performance with single-level features.”