BriefGPT.xyz
Sep, 2021
Pix2seq: 一种用于目标检测的语言建模框架
Pix2seq: A Language Modeling Framework for Object Detection
HTML
PDF
Ting Chen, Saurabh Saxena, Lala Li, David J. Fleet, Geoffrey Hinton
TL;DR
Pix2Seq是一种简单且通用的目标检测框架,不同于现有的方法,它将目标检测视为一种基于观察像素输入的语言建模任务,并通过训练神经网络来感知图像并生成所需的序列,与高度专业化和精心优化的检测算法相比,在具有挑战性的COCO数据集上实现了有竞争力的结果
Abstract
This paper presents
pix2seq
, a simple and generic framework for
object detection
. Unlike existing approaches that explicitly integrate prior knowledge about the task, we simply cast
→