Conventional approaches to Sketch-Based Image Retrieval (SBIR) assume that the data of all the classes are available during training. The assumption may not always be practical since the data of a few classes may be unavailable, or the classes may not appear at the time of training. Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) relaxes this constraint and allows the algorithm to handle previously unseen classes during the test. This paper proposes a generative approach based on the Stacked Adversarial Network (SAN) and the advantage of Siamese Network (SN) for ZS-SBIR. While SAN generates a high-quality sample, SN learns a better distance metric compared to that of the nearest neighbor search. The capability of the generative model to synthesize image features based on the sketch reduces the SBIR problem to that of an image-to-image retrieval problem. We evaluate the efficacy of our proposed approach on TU-Berlin, and Sketchy database in both standard ZSL and generalized ZSL setting. The proposed method yields a significant improvement in standard ZSL as well as in a more challenging generalized ZSL setting (GZSL) for SBIR.

中文翻译：

---

用于基于零镜头草图的图像检索的堆叠对抗网络

基于草图的图像检索 (SBIR) 的传统方法假设所有类的数据在训练期间都可用。由于少数类的数据可能不可用，或者这些类可能在训练时未出现，因此该假设可能并不总是可行的。基于零镜头草图的图像检索 (ZS-SBIR) 放宽了此约束，并允许算法在测试期间处理以前未见过的类。本文提出了一种基于堆叠对抗网络（SAN）和连体网络（SN）优势的生成方法，用于 ZS-SBIR。虽然 SAN 生成了高质量的样本，但与最近邻搜索相比，SN 学习了更好的距离度量。生成模型基于草图合成图像特征的能力将 SBIR 问题简化为图像到图像检索问题。我们在标准 ZSL 和广义 ZSL 设置中评估了我们提出的方法在 TU-Berlin 和 Sketchy 数据库上的功效。所提出的方法在标准 ZSL 以及用于 SBIR 的更具挑战性的广义 ZSL 设置 (GZSL) 中产生了显着改进。