Large Scale image classification is a challenging problem within the field of computer vision. As the real world contains billions of different objects, understanding the performance of popular techniques and models is vital in order to apply them to real world tasks. In this paper, we evaluate techniques and popular CNN based deep learning architectures to perform large scale species classification on the dataset from iNaturalist 2019 Challenge. Methods utilizing dataset pruning and transfer learning are shown to outperform models trained without either of the two techniques. The ResNext based classifier outperforms other model architectures over 10 epochs and achieves a top-one validation error of 0.68 when classifying amongst the 1,010 species.
翻译:大型图像分类在计算机视觉领域是一个具有挑战性的问题。 由于真实世界包含数十亿个不同对象,了解流行技术和模型的性能对于将其应用于现实世界任务至关重要。 在本文中,我们评估技术和流行的有线电视新闻网的深层学习结构,以便在iNatulist 2019 挑战的数据集中进行大规模物种分类。 利用数据集的剪裁和传输学习的方法在没有两种技术的情况下显示优于所培训的模型。 基于 ResNext 的分类优于超过10 个世纪的其他模型结构,在对1 010 种物种进行分类时,实现了0.68 的顶级验证错误。