[OLN] Learning Open-World Object Proposals without Learning to Classify

最新推荐文章于 2023-10-27 11:07:44 发布

Ah丶Weii

最新推荐文章于 2023-10-27 11:07:44 发布

阅读量1k

点赞数 1

分类专栏：笔记文章标签：深度学习机器学习

本文链接：https://blog.csdn.net/weixin_43823854/article/details/120127654

版权

本文提出了一种名为Object Localization Network (OLN)的方法，旨在学习纯定位对象性，以提高对未见过类别的一般化能力。OLN通过去除分类器，避免过拟合，从而改进了RPN和 Faster R-CNN。实验表明，OLN在跨类别和跨数据集设置上表现出色，尤其是在处理长尾检测和第一人称视频方面。

摘要由CSDN通过智能技术生成

1. Motivation

Our main insight is that the classifiers in existing object proposers or class agnostic detectors impedes such generalization, because the model tends to overfit to labeled objects and treat the unlabeled objects in the training set as background.
This matches the ability of human to detect novel objects in new environments without naming their categories

2. Contribution

To our knowledge, we are the first to show the value of pure localization-based objectness learning for novel object proposals, and propose a simple-yet-effective classifier-free Object Localization Network (OLN).
Our approach outperforms state-of-the-art methods on cross-category setting on COCO and improves cross- dataset settings on RoboNet and Object365, long-tail detection (LVIS) and egocentric videos (EpicKitchens) over the standard approach.
We carefully annotated the RoboNet dataset for the presence of all objects in an exhaustive fashion. We perform open-world class-agnostic object detection, and evaluate the Average Precision, which also improves existing AR-based evaluation of proposals on partially-annotated data.
Extensive ablation and analysis on OLN modeling choices reveal the benefits of each localization cue and the overfitting of existing classifier-based methods.