CamoTeacher：面向半监督伪装目标检测的双旋转一致性学习
CamoTeacher: Dual-Rotation Consistency Learning for Semi-Supervised Camouflaged Object Detection
AI总结：
针对半监督伪装目标检测中伪标签噪声问题，提出CamoTeacher框架，通过双旋转一致性学习分别处理像素级与实例级噪声，性能超越现有半监督方法且可匹敌全监督方法。
摘要：
现有伪装目标检测（COD）方法严重依赖大规模像素级标注，然而由于目标固有的伪装特性，获取这类标注十分耗费人力。半监督学习为这一挑战提供了有前景的解决方案，但其在COD中的应用受限于像素级和实例层面的大量伪标签噪声。我们提出了一种新型半监督COD框架CamoTeacher，采用双旋转一致性学习（DRCL）有效解决这些噪声问题。具体而言，DRCL利用旋转视角在像素级和实例级的一致性来降低伪标签噪声：首先，它采用像素级一致性学习（PCL）通过对伪标签内不同部分重新加权来处理像素级噪声；其次，使用实例级一致性学习（ICL）调整伪标签权重，以处理实例级噪声。在四个COD基准数据集上开展的大量实验表明，所提出的CamoTeacher不仅在半监督学习方法中达到了当前最优水平，还能与成熟的全监督学习方法相媲美。我们的代码即将公开。
英文摘要：
Existing camouflaged object detection~(COD) methods depend heavily on large-scale pixel-level annotations.However, acquiring such annotations is laborious due to the inherent camouflage characteristics of the objects.Semi-supervised learning offers a promising solution to this challenge.Yet, its application in COD is hindered by significant pseudo-label noise, both pixel-level and instance-level.We introduce CamoTeacher, a novel semi-supervised COD framework, utilizing Dual-Rotation Consistency Learning~(DRCL) to effectively address these noise issues.Specifically, DRCL minimizes pseudo-label noise by leveraging rotation views' consistency in pixel-level and instance-level.First, it employs Pixel-wise Consistency Learning~(PCL) to deal with pixel-level noise by reweighting the different parts within the pseudo-label.Second, Instance-wise Consistency Learning~(ICL) is used to adjust weights for pseudo-labels, which handles instance-level noise.Extensive experiments on four COD benchmark datasets demonstrate that the proposed CamoTeacher not only achieves state-of-the-art compared with semi-supervised learning methods, but also rivals established fully-supervised learning methods.Our code will be available soon.
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。
