Morphable Detector for Object Detection on Demand
Morphable Detector for Object Detection on Demand
复制标题
DOI：
10.1109/iccv48922.2021.00473
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Xiangyun Zhao;Xu Zou;Ying Wu
中科院分区：
文献类型：
--
作者：
Xiangyun Zhao;Xu Zou;Ying Wu
智能机器人的许多新兴应用需要探索和理解新环境，在这些环境中，需要以最小的在线工作量动态检测新类别的对象。这是一个按需对象检测 (ODOD) 任务。这是具有挑战性的，因为不可能动态注释大量数据，并且嵌入式系统通常无法执行对于训练至关重要的反向传播。大多数现有的小样本检测方法都面临着这里的问题，因为它们需要额外的训练。我们提出了一种新颖的可变形检测器（MD），它简单地“变形”从少数样本在线估计的一些可变参数，以便在不需要任何额外训练的情况下检测新的类别。 MD 有两组参数，一组用于特征嵌入，另一组用于类表示（称为“原型”）。每个类都与一个隐藏的原型相关联，可以通过集成视觉和语义嵌入来学习。 MD 的学习基于特征嵌入和类似 EM 方法中的原型的交替学习，该方法允许从新类别的几个样本中恢复未知原型。一旦学习了 MD，它就能够使用新类的一些样本来直接计算其原型来完成在线变形过程。我们已经在 Pascal [12]、COCO [27] 和 FSOD [13] 数据集中展示了 MD 的优越性。
Many emerging applications of intelligent robots need to explore and understand new environments, where it is desirable to detect objects of novel classes on the fly with minimum online efforts. This is an object detection on demand (ODOD) task. It is challenging, because it is impossible to annotate a large number of data on the fly, and the embedded systems are usually unable to perform back-propagation which is essential for training. Most existing few-shot detection methods are confronted here as they need extra training. We propose a novel morphable detector (MD), that simply "morphs" some of its changeable parameters online estimated from the few samples, so as to detect novel classes without any extra training. The MD has two sets of parameters, one for the feature embedding and the other for class representation (called "prototypes"). Each class is associated with a hidden prototype to be learned by integrating the visual and semantic embeddings. The learning of the MD is based on the alternate learning of the feature embedding and the prototypes in an EM-like approach which allows the recovery of an unknown prototype from a few samples of a novel class. Once an MD is learned, it is able to use a few samples of a novel class to directly compute its prototype to fulfill the online morphing process. We have shown the superiority of the MD in Pascal [12], COCO [27] and FSOD [13] datasets.