Abstract

Training Convolutional Neural Networks that do well in one-shot learning settings can have wide range of impacts on real-world datasets. In this paper, we explore an adversarial training method that learns a Siamese neural network in an end-to-end fashion for two models—ConvNets model that learns image embeddings from input image pair, and head model that further learns the distance between those embeddings. We further present an adversarial mining approach that efficiently identifies and selects harder examples during training, which significantly boosts the model performance over difficult cases. We have done a comprehensive evaluation using a public whale identification dataset hosted on Kaggle platform, and report state-of-the-art performance benchmarking against result of other 2000 participants.

中文翻译：

---

连体网和对抗训练的鲸鱼重新识别方法

摘要

训练在一次学习设置中表现出色的卷积神经网络可能会对现实世界的数据集产生广泛的影响。在本文中，我们探索了一种对抗训练方法，该方法以两种模式以端到端的方式学习暹罗神经网络：ConvNets模型从输入图像对中学习图像嵌入；头部模型进一步学习这些嵌入之间的距离。我们进一步提出了一种对抗挖掘方法，该方法可以在训练过程中有效地识别和选择更难的示例，从而在困难情况下显着提高模型的性能。我们使用Kaggle平台上托管的公共鲸鱼识别数据集进行了全面评估，并针对其他2000名参与者的结果报告了最新的性能基准。