CASIA OpenIR  > 毕业生  > 硕士学位论文
开放集目标检测方法研究
熊永誉
2022-05-29
页数90
学位类型硕士
中文摘要

基于卷积神经网络的目标检测方法在众多视觉任务上取得了很大的成功,然
而大多数现有的目标检测方法是基于封闭类别集假设来设计的,只能对场景中
出现的预定类别的物体进行检测,而未训练过的类别的物体往往作为背景被忽
略掉。为此,本文研究开放集目标检测方法,使其能够在检测出预定类别目标的
同时,将未知类别的目标也检测出来并标记为未知类。本文探索提出了几种方法
并开展了实验验证。主要工作和贡献如下:
1. 提出一种基于异常目标拒绝的开放集目标检测方法。该方法将现有的检
测算法与开放集识别算法相结合,并使用one-versus-all 准则进行训练,打破常
规检测算法中分类器的封闭集假设,实现未知类别目标的发现。在自然场景未知
类别昆虫检测任务上,取得了满意的效果。
2. 提出一种基于原型学习的一阶段开放集目标检测方法。该方法将原型分
类机制引入检测算法中,利用原型分类器可以在特征空间中形成紧凑的类内分
布和松散的类间分布,在保持对已知类物体检测性能的同时,有效地提高了检测
器对未知类目标的检测能力。在PASCAL VOC 数据集上的实验表明,本方法能
够在保证已知类别目标检测性能的同时,有效鉴别出未知类别的目标。
3. 提出一种基于显著性引导的训练策略。该策略以图像中的显著性信息为
线索,引导检测器对图中未标注的目标区域做出更有效的响应,从而克服了训练
图片中未标记目标对新类别发现造成的不利影响,使算法能够利用更多的数据
对模型进行充分训练,有效地提高对未知类目标的发现能力。在PASCAL VOC
数据集上的实验表明,本方法对基于CenterNet 的开放集目标检测器有效提升了
目标发现性能。

英文摘要

Object detection methods based on convolutional neural networks have achieved great success in many computer vision tasks. However, most existing object detection methods are designed based on the hypothesis of closed category set, and thus, can only detect objects of predetermined categories appearing in the training set, while ignoring objects of unknown categories as background. Therefore, this thesis focuses on open set object detection, aiming to detect objects of unknown categories and mark them as unknown categories while detecting the objects of predetermined categories. Several methods are proposed and their effectiveness is verified in experiments. The main contributions are as follows:
1. An open set object detection method based on the rejection of abnormal objects is proposed. This method combines the existing detection algorithm with the open set recognition algorithm, and uses the one-versus-all criterion for training, breaking the closed set assumption of the classification layer in the conventional detection algorithm, so as to enable the discovery of unknown category objects. Satisfactory results have been achieved on the task of detecting unknown insects in natural scenes.
2. A one-stage open-set object detection method based on prototype learning is proposed. This method uses the prototype based classifier to form a compact intraclass distribution and a scattered inter-class distribution in the feature space. This can effectively improve the unknown object detection performance while maintaining the detection ability of known objects. Experiments on PASCAL VOC datasets show that
the proposed method can effectively identify unknown class objects while ensuring the detection performance of known class objects.
3. A training strategy based on saliency guidance is proposed. It uses the saliency information in the image as a clue to guide the detector to respond positively to the unlabeled object regions in the image, thereby overcoming the adverse effect of unlabeled foreground objects in the training image on the discovery of new categories. At the same time, the algorithm can use more data to fully train the model and effectively improve the ability to discover unknown targets. Experiments on the PASCAL VOC dataset show that our proposed strategy significantly improves the performance of the CenterNet-based open-set object detector on object discovery tasks.

关键词目标检测 开放集识别 原型学习 开放集目标检测
学科领域计算机科学技术 ; 人工智能
学科门类工学 ; 工学::计算机科学与技术(可授工学、理学学位)
语种中文
文献类型学位论文
条目标识符http://ir.ia.ac.cn/handle/173211/48830
专题毕业生_硕士学位论文
推荐引用方式
GB/T 7714
熊永誉. 开放集目标检测方法研究[D]. 中国科学院自动化研究所. 中国科学院自动化研究所,2022.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
熊永誉_硕士论文_最终版.pdf(10765KB)学位论文 限制开放CC BY-NC-SA
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[熊永誉]的文章
百度学术
百度学术中相似的文章
[熊永誉]的文章
必应学术
必应学术中相似的文章
[熊永誉]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。