Semi-supervised contrastive clustering with strong-weak augmentation for novel class discovery in open-world object detection

计算机科学 聚类分析 目标检测 人工智能 帕斯卡(单位) 稳健性(进化) 注释 模式识别(心理学) 分类器(UML) 对象(语法) 班级(哲学) 噪音(视频) 精确性和召回率 机器学习 钥匙(锁) 源代码 训练集 数据挖掘 特征提取 组分(热力学) 监督学习 标记数据 编码(集合论) 视觉对象识别的认知神经科学 特征学习
作者
Fei Wang,Rui Ma
出处
期刊:Journal of King Saud University - Computer and Information Sciences [Elsevier BV]
卷期号:37 (9): 296- 被引量:3
标识
DOI:10.1007/s44443-025-00329-3
摘要

Unknown objects in open-world scenarios pose significant challenges to object detection accuracy. Existing open-set detection methods often rely on manual annotation of unknown objects followed by incremental learning, which is both time-consuming and labor-intensive. To discover the potential categories of unknown objects and reduce the cost of manual annotation, we propose OWDet, an open-world object detection framework designed to automatically discover and learn new object concepts. A key component of OWDet is a semi-supervised contrastive clustering with strong-weak augmentation algorithm that effectively organizes unknown objects into distinct clusters. By leveraging labels from known objects, the algorithm guides the clustering process, facilitating the discovery of novel concepts that may not exist in the original training set. To ensure reliability, a cluster filtering mechanism is introduced to generate pseudo-labels only for high-confidence clusters, thereby reducing noise and improving learning efficiency. Once novel classes are identified, they are combined with known categories to retrain the detector, enhancing its overall detection performance. Extensive experiments on a composite dataset combining KITTI, Pascal VOC, and MS COCO demonstrate that OWDet significantly outperforms existing methods in open-world scenarios. Notably, it achieves a 94.7% purity in new category discovery across 942 unknown samples. Furthermore, OWDet maintains high detection recall on cross-domain tests without fine-tuning, confirming its robustness in open-world environments. Our source code is available at https://github.com/StarkM10/OWDet .

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Jasper的应助被科研通管家采纳,获得10
刚刚
小蘑菇的应助被开心德地采纳,获得20
刚刚
刚刚
刚刚
bkagyin的应助被科研通管家采纳,获得10
刚刚
缄默发布了新的文献求助10
刚刚
刚刚
科目三的应助被科研通管家采纳,获得10
刚刚
缄默发布了新的文献求助10
1秒前
小蘑菇的应助被Jeremy采纳,获得10
1秒前
Youdge的应助被科研通管家采纳,获得20
1秒前
1秒前
1秒前
小二郎的应助被科研通管家采纳,获得10
1秒前
李爱国的应助被科研通管家采纳,获得10
1秒前
脑洞疼的应助被科研通管家采纳,获得10
1秒前
Maestro_S的应助被科研通管家采纳,获得10
1秒前
1秒前
上官若男的应助被科研通管家采纳,获得10
1秒前
1秒前
科目三的应助被Mason采纳,获得30
2秒前
华仔的应助被科研通管家采纳,获得10
2秒前
2秒前
Owen的应助被科研通管家采纳,获得10
2秒前
2秒前
顾矜的应助被科研通管家采纳,获得10
2秒前
FashionBoy的应助被郝子凯采纳,获得10
2秒前
Jasper的应助被科研通管家采纳,获得10
2秒前
大模型的应助被科研通管家采纳,获得30
2秒前
2秒前
整齐从蓉发布了新的文献求助10
3秒前
无花果的应助被科研通管家采纳,获得10
3秒前
3秒前
3秒前
汉堡包的应助被科研通管家采纳,获得10
3秒前
syvshc的应助被科研通管家采纳,获得10
3秒前
聪明机器猫完成签到,获得积分10
3秒前
3秒前
脑洞疼的应助被科研通管家采纳,获得10
3秒前
3秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8187652
求助须知:如何正确求助?哪些是违规求助? 9575758
关于积分的说明 21842805
捐赠科研通 7785538
什么是DOI,文献DOI怎么找? 3435073
关于科研通互助平台的介绍 2559480
邀请新用户注册赠送积分活动 2481963