You Only Look One-level Feature

03/17/2021
by   Qiang Chen, et al.
17

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. With an image size of 608×608, YOLOF achieves 44.3 mAP running at 60 fps on 2080Ti, which is 13% faster than YOLOv4. Code is available at <https://github.com/megvii-model/YOLOF>.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/16/2022

You Should Look at All Objects

Feature pyramid network (FPN) is one of the key components for object de...
06/26/2021

Real-time 3D Object Detection using Feature Map Flow

In this paper, we present a real-time 3D detection approach considering ...
10/28/2021

LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image

X-ray image plays an important role in manufacturing for quality assuran...
07/17/2017

Residual Features and Unified Prediction Network for Single Stage Detection

Recently, a lot of single stage detectors using multi-scale features hav...
06/01/2021

You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection

Can Transformer perform 2D object-level recognition from a pure sequence...
07/16/2020

RepPoints V2: Verification Meets Regression for Object Detection

Verification and regression are two general methodologies for prediction...
12/06/2020

Towards Better Object Detection in Scale Variation with Adaptive Feature Selection

It is a common practice to exploit pyramidal feature representation to t...

Code Repositories

YOLOF

You Only Look One-level Feature (YOLOF), CVPR2021, Detectron2


view repo