Delta-encoder: an effective sample synthesis method for few-shot object recognition
Delta-encoder: an effective sample synthesis method for few-shot object recognition
复制标题
DOI：
--
复制
发表时间：
2018-06
期刊：
影响因子：
--
通讯作者：
Eli Schwartz;Leonid Karlinsky;J. Shtok;Sivan Harary;Mattias Marder;Abhishek Kumar;R. Feris;R. Giryes-R.
中科院分区：
文献类型：
--
作者：
Eli Schwartz;Leonid Karlinsky;J. Shtok;Sivan Harary;Mattias Marder;Abhishek Kumar;R. Feris;R. Giryes-R.
学习根据一个或几个例子对新类别进行分类是现代计算机视觉中的一个长期挑战。在这项工作中，我们提出了一个简单而有效的方法，少数拍摄（和一杆）的对象识别。我们的方法是基于一个修改后的自动编码器，表示为Delta-encoder，学习合成新的样本，为一个看不见的类别，只是看到它的一些例子。合成的样本，然后用来训练分类器。所提出的方法学习在训练示例的同类对之间提取可转移的类内变形或“增量”，并将这些增量应用于新类的少数提供的示例（在训练期间看不见），以便有效地合成来自该新类的样本。所提出的方法改进了国家的最先进的单镜头目标识别和比较有利的情况下，在少数拍摄。接受后，代码将提供。
Learning to classify new categories based on just one or a few examples is a long-standing challenge in modern computer vision. In this work, we proposes a simple yet effective method for few-shot (and one-shot) object recognition. Our approach is based on a modified auto-encoder, denoted Delta-encoder, that learns to synthesize new samples for an unseen category just by seeing few examples from it. The synthesized samples are then used to train a classifier. The proposed approach learns to both extract transferable intra-class deformations, or "deltas", between same-class pairs of training examples, and to apply those deltas to the few provided examples of a novel class (unseen during training) in order to efficiently synthesize samples from that new class. The proposed method improves over the state-of-the-art in one-shot object-recognition and compares favorably in the few-shot case. Upon acceptance code will be made available.