论文标题
通过对比度优化属性表示来增强零射击学习
Boosting Zero-shot Learning via Contrastive Optimization of Attribute Representations
论文作者
论文摘要
零射门学习（ZSL）旨在识别培训集中没有样本的类。一种代表性的解决方案是直接学习一个嵌入功能，将视觉特征与相应的类语义相关联，以识别新类。许多方法扩展了这种解决方案，最近的方法特别热衷于从图像中提取丰富的特征，例如属性功能。这些属性特征通常在每个单独的图像中提取；但是，不强调跨图像的特征的共同特征。在本文中，我们提出了一个新的框架来通过明确学习原型超出图像来提高ZSL，并用图像中的属性级特征对其进行对比优化它们。除了新颖的体系结构外，要为属性表示强调了两个元素：新的原型生成模块旨在从属性语义中生成属性原型；引入了基于硬示例的对比优化方案，以增强嵌入空间中的属性级特征。我们探索了两个基于CNN的替代骨架，基于CNN的骨架，以建立我们的框架并在三个标准基准测试（Cub，Sun，Awa2）上进行实验。这些基准测试的结果表明，我们的方法通过相当大的利润改善了最新技术的状态。我们的代码将在https://github.com/dyabel/coar-zsl.git上找到
Zero-shot learning (ZSL) aims to recognize classes that do not have samples in the training set. One representative solution is to directly learn an embedding function associating visual features with corresponding class semantics for recognizing new classes. Many methods extend upon this solution, and recent ones are especially keen on extracting rich features from images, e.g. attribute features. These attribute features are normally extracted within each individual image; however, the common traits for features across images yet belonging to the same attribute are not emphasized. In this paper, we propose a new framework to boost ZSL by explicitly learning attribute prototypes beyond images and contrastively optimizing them with attribute-level features within images. Besides the novel architecture, two elements are highlighted for attribute representations: a new prototype generation module is designed to generate attribute prototypes from attribute semantics; a hard example-based contrastive optimization scheme is introduced to reinforce attribute-level features in the embedding space. We explore two alternative backbones, CNN-based and transformer-based, to build our framework and conduct experiments on three standard benchmarks, CUB, SUN, AwA2. Results on these benchmarks demonstrate that our method improves the state of the art by a considerable margin. Our codes will be available at https://github.com/dyabel/CoAR-ZSL.git
