面向细粒度草图检索的对抗训练三元组网络

将草图作为检索示例用于图像检索称之为基于草图的图像检索.在这其中，细粒度检索问题或类内检索问题是2014年被研究者提出并快速成为广受关注的研究方向.目前研究者通常用三元组网络来解决类内检索问题，且取得了不错的效果.但是三元组网络的训练非常困难，很多情况下很难收敛甚至不收敛，且存在着容易过拟合的风险.本文借鉴循环生成对抗训练的思想，设计了SketchCycleGAN帮助提高三元组网络训练过程的效率，以对抗训练的方式使其参与到三元组网络的训练过程中，通过充分挖掘数据集自身信息的方式取代了利用其他数据集进行预训练的过程，在简化训练步骤的基础上取得了更好的检索性能.通过在常用的细粒度草图检索数据集上的一系列对比实验，证明了所提方法的有效性和优越性.

Adversarial Training Triplet Network for Fine-grained Sketch Based Image Retrieval

Sketch based image retrieval means that the sketch is used as the query in the retrieval. Fine-grained image retrieval or intra-category retrieval was proposed in 2014 and attracted more attentions quickly. Triplet network is often used to do fine-grained retrieval and get promising performance. However, training triplet network is quite difficult, it is hard to converge and easy to over-fit in some situations. Inspired by the adversarial training, this paper proposes SketchCycleGAN to improve the efficiency of the triplet network training process. In this proposal, pre-training the networks with other database is replaced by mining the information inside the database with the help of adversarial training. That could simplify the training procedure with better performance. This proposal could get better performance than other state-of-the-art methods in a series of experiments executed on widely used databases for fine-grained sketch based retrieval.