论文标题
使用未标记的数据来提高相关和开放式图像的低射击分类精度
Using Unlabeled Data for Increasing Low-Shot Classification Accuracy of Relevant and Open-Set Irrelevant Images
论文作者
论文摘要
在搜索，探索和侦察任务中使用自动地面车辆执行的任务，需要专门识别目标对象（相关类）的图像分类能力，同时识别何时候选图像不属于相关类（无关图像）的任何人。在本文中，我们提供了一个开放式低弹药分类器，该分类器在培训期间使用每个相关类别的标记图像（少于40）的标记图像，并且在训练过程的每个时期中随机选择了无标记的无关图像。新的分类器能够识别来自相关类别的图像，确定候选图像何时无关紧要，并且可以进一步识别培训中未包含的无关图像的类别（看不见）。构建卷积神经网络时，提出的低弹药分类器可以作为顶层作为顶层附加到任何预训练的特征提取器。
In search, exploration, and reconnaissance tasks performed with autonomous ground vehicles, an image classification capability is needed for specifically identifying targeted objects (relevant classes) and at the same time recognize when a candidate image does not belong to anyone of the relevant classes (irrelevant images). In this paper, we present an open-set low-shot classifier that uses, during its training, a modest number (less than 40) of labeled images for each relevant class, and unlabeled irrelevant images that are randomly selected at each epoch of the training process. The new classifier is capable of identifying images from the relevant classes, determining when a candidate image is irrelevant, and it can further recognize categories of irrelevant images that were not included in the training (unseen). The proposed low-shot classifier can be attached as a top layer to any pre-trained feature extractor when constructing a Convolutional Neural Network.
