Sketch-an-Anchor is a novel method to train state-of-the-art Zero-shot Sketch-based Image Retrieval (ZSSBIR) models in under an epoch. Most studies break down the problem of ZSSBIR into two parts: domain alignment between images and sketches, inherited from SBIR, and generalization to unseen data, inherent to the zero-shot protocol. We argue one of these problems can be considerably simplified and re-frame the ZSSBIR problem around the already-stellar yet underexplored Zero-shot Image-based Retrieval performance of off-the-shelf models. Our fast-converging model keeps the single-domain performance while learning to extract similar representations from sketches. To this end we introduce our Semantic Anchors -- guiding embeddings learned from word-based semantic spaces and features from off-the-shelf models -- and combine them with our novel Anchored Contrastive Loss. Empirical evidence shows we can achieve state-of-the-art performance on all benchmark datasets while training for 100x less iterations than other methods.

翻译：草图锚点是一种新颖方法，可在不到一个训练周期内训练出最先进的零样本草图图像检索（ZSSBIR）模型。大多数研究将ZSSBIR问题分解为两部分：继承自SBIR的图像与草图之间的域对齐，以及零样本协议固有的对未见数据的泛化能力。我们认为其中一个问题可大幅简化，并将ZSSBIR问题围绕现成模型已出色但未充分探索的零样本基于图像检索性能进行重构。我们的快速收敛模型在保持单域性能的同时，学习从草图中提取相似表示。为此，我们引入了语义锚点——从基于词的语义空间和现成模型特征中学习到的引导嵌入——并将其与新型锚定对比损失相结合。实证证据表明，我们可在所有基准数据集上实现最先进性能，同时训练迭代次数比其他方法少100倍。