互联网商品图像的属性分类是人工智能领域的重要研究课题之一,针对商品图像属性分布不平衡以及不同属性间存在相关性等问题,该文以女装图像为分类目标,提出了一种基于卷积神经网络的商品图像分类方法.首先,从电商网站获取大量商品图像,并进行人工标注;然后,基于卷积神经网络框架,采用了一种有效的采样策略,通过增加新的损失函数,实现了基于多任务学习方法的商品图像属性准确分类;最后,通过对不同策略下分类结果的对比分析,验证了该方法的有效性.结果显示,所提出方法具有较高的分类精度.“,”With the rapid development of lnternet online shopping, automatic classification of product images has become an interesting research topic. In this paper, an accurate classification method for women dress images are investigated. Firstly, 40 000 product images were crawled from the Vipshop online shopping websites, which all are annotated by several experts. Then, several baselines using deep convolutional networks were provided. Finally, a new loss function was introduced and the multi-task learning method was used to improve the classification accuracy. With the comparison of different strategies, the experimental results show that the proposed method can obtain higher classification accuracy.