arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.12756cs.CV
收藏

一种新的开集图像识别网络训练方法

A novel network training approach for open set image recognition

Federation University(联邦大学);Murdoch University(莫道克大学)

Md Tahmid Hossain, Shyh Wei Teng, Guojun Lu, Ferdous Sohel

摘要:

卷积神经网络(CNN)通常被设计用于闭集排列,其中测试实例仅属于训练中使用的一些“已知已知”(KK)类。因此,他们根据KK类的分布预测测试样本的类标签。然而,当在开集识别(OSR)设置下使用时(其中输入可能属于“未知未知”或UU类),这样的网络将始终将测试实例分类为KK类之一,即使它来自UU类。作为一种解决方案,最近,已经使用了基于生成对抗网络(GAN)的数据增强。在这项工作中,我们提出了一种新的方法来挖掘“已知未知训练器”或KUT集,并设计了一个深度OSR网络(OSRNet)来利用这个数据集。我们的目标是通过KUT集教OSRNet UU的本质,KUT集实际上是一个挖掘的“硬已知未知否定”的集合。一旦经过训练,OSRNet可以检测UU,同时保持KK的高分类精度。我们在六个基准数据集上评估了OSRNet,并证明它优于当代OSR方法。

英文摘要:

Convolutional Neural Networks (CNNs) are commonly designed for closed set arrangements, where test instances only belong to some "Known Known" (KK) classes used in training. As such, they predict a class label for a test sample based on the distribution of the KK classes. However, when used under the Open Set Recognition (OSR) setup (where an input may belong to an "Unknown Unknown" or UU class), such a network will always classify a test instance as one of the KK classes even if it is from a UU class. As a solution, recently, data augmentation based on Generative Adversarial Networks(GAN) has been used. In this work, we propose a novel approach for mining a "Known UnknownTrainer" or KUT set and design a deep OSR Network (OSRNet) to harness this dataset. The goal isto teach OSRNet the essence of the UUs through KUT set, which is effectively a collection of mined "hard Known Unknown negatives". Once trained, OSRNet can detect the UUs while maintaining high classification accuracy on KKs. We evaluate OSRNet on six benchmark datasets and demonstrate it outperforms contemporary OSR methods.

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。

↑