arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.14960cs.CV
收藏

用于密集目标检测的抗模糊半监督学习

Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection

Shanghai University(上海大学);Baidu Inc(百度公司);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)

Chang Liu, Weiming Zhang, Xiangru Lin, Wei Zhang, Xiao Tan, Junyu Han, Xiaomao Li, Errui Ding, Jingdong Wang

摘要:

对于基本的半监督目标检测(SSOD)技术,与两阶段聚类相比,一阶段检测器通常获得有限的提升。我们通过实验发现,根源在于两种歧义:(1)选择歧义,选择伪标签是不准确的,因为分类分数不能正确地代表本地化质量。(2)分配模糊性,即在伪标签分配中,样本与不正确的标签匹配,因为该策略被遗漏的对象和不准确的伪框误导。为了解决这些问题,我们提出了一个抗歧义的半监督学习(ARSL)的一阶段检测器。具体而言,为了减轻选择模糊性,联合置信度估计(JCE)提出了联合量化的分类和定位质量的伪标签。对于分配模糊性,任务分离分配(TSA)被引入到基于像素级预测而不是不可靠的伪框来分配标签。它采用了“分而治之”的策略,并分别利用积极的分类和定位任务,这是更强大的分配模糊。综合实验表明,ARSL有效地减轻了歧义,并实现了最先进的SSOD性能的MS COCO和PASCAL VOC。代码可以在https://github.com/PaddlePaddle/PaddleDetection上找到。

英文摘要:

With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage detectors generally obtain limited promotions compared with two-stage clusters. We experimentally find that the root lies in two kinds of ambiguities: (1) Selection ambiguity that selected pseudo labels are less accurate, since classification scores cannot properly represent the localization quality. (2) Assignment ambiguity that samples are matched with improper labels in pseudo-label assignment, as the strategy is misguided by missed objects and inaccurate pseudo boxes. To tackle these problems, we propose a Ambiguity-Resistant Semi-supervised Learning (ARSL) for one-stage detectors. Specifically, to alleviate the selection ambiguity, Joint-Confidence Estimation (JCE) is proposed to jointly quantifies the classification and localization quality of pseudo labels. As for the assignment ambiguity, Task-Separation Assignment (TSA) is introduced to assign labels based on pixel-level predictions rather than unreliable pseudo boxes. It employs a "divide-and-conquer" strategy and separately exploits positives for the classification and localization task, which is more robust to the assignment ambiguity. Comprehensive experiments demonstrate that ARSL effectively mitigates the ambiguities and achieves state-of-the-art SSOD performance on MS COCO and PASCAL VOC. Codes can be found at https://github.com/PaddlePaddle/PaddleDetection.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑