PAFNet: An Efficient Anchor-Free Object Detector Guidance

by   Ying Xin, et al.

Object detection is a basic but challenging task in computer vision, which plays a key role in a variety of industrial applications. However, object detectors based on deep learning usually require greater storage requirements and longer inference time, which hinders its practicality seriously. Therefore, a trade-off between effectiveness and efficiency is necessary in practical scenarios. Considering that without constraint of pre-defined anchors, anchor-free detectors can achieve acceptable accuracy and inference speed simultaneously. In this paper, we start from an anchor-free detector called TTFNet, modify the structure of TTFNet and introduce multiple existing tricks to realize effective server and mobile solutions respectively. Since all experiments in this paper are conducted based on PaddlePaddle, we call the model as PAFNet(Paddle Anchor Free Network). For server side, PAFNet can achieve a better balance between effectiveness (42.2 (67.15 FPS) on a single V100 GPU. For moblie side, PAFNet-lite can achieve a better accuracy of (23.9 the existing state-of-the-art anchor-free detectors by significant margins. Source code is at



There are no comments yet.


page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 8


PP-YOLO: An Effective and Efficient Implementation of Object Detector

Object detection is one of the most important areas in computer vision, ...

Training-Time-Friendly Network for Real-Time Object Detection

Modern object detectors can rarely achieve short training time, fast inf...

PP-YOLOv2: A Practical Object Detector

Being effective and efficient is essential to an object detector for pra...

Anchor DETR: Query Design for Transformer-Based Detector

In this paper, we propose a novel query design for the transformer-based...

Efficient Person Search: An Anchor-Free Approach

Person search aims to simultaneously localize and identify a query perso...

FCHD: A fast and accurate head detector

In this paper, we propose FCHD-Fully Convolutional Head Detector, which ...

YOLOX: Exceeding YOLO Series in 2021

In this report, we present some experienced improvements to YOLO series,...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.