SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.09460 · CVPR · 2021

You Only Look One-level Feature

Xiangyu Zhang, Jian Sun, Qiang Chen, Jian Cheng, Tong Yang, Yingming Wang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2103.09460")
get_code_for_paper("2103.09460")
have("2103.09460")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2103.09460.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2103.09460.svg)](https://syntology.ai/paper/2103.09460)

Connect an agent — have() is free.