BriefGPT.xyz
Nov, 2019
通过样式一致性进行目标检测的领域自适应
Domain Adaptation for Object Detection via Style Consistency
HTML
PDF
Adrian Lopez Rodriguez, Krystian Mikolajczyk
TL;DR
本文提出了一种基于领域自适应的目标检测方法，使用风格迁移和伪标签方法，使检测器在不同图像样式下具有鲁棒性，并显著提升了性能。
Abstract
We propose a
domain adaptation
approach for
object detection
. We introduce a two-step method: the first step makes the detector robust to low-level differences and the second step adapts the classifiers to change
→