论文标题
从广义的零射门学习到长尾描述符
From Generalized zero-shot learning to long-tail with class descriptors
论文作者
论文摘要
现实世界中的数据主要是不平衡和长尾巴的，但是深层模型却难以在频繁的类别存在下识别稀有类别。通常，课程可以与文本描述这样的附带信息伴随，但是尚不完全清楚如何将它们用于学习不平衡的长尾数据。此类描述主要用于（广义）零击学习（ZSL），这表明带有类描述的ZSL也可能对长尾分布有用。我们描述了龙，这是一种与班级描述符的长尾学习的后期结构。它学会了（1）按样本基础纠正偏见对头部的偏见； （2）从类描述的信息融合信息，以提高尾部准确性。我们还介绍了新的基准测试CUB-LT，SUN-LT，AWA-LT，用于长尾学习，具有类描述，基于现有学习数据集的基于数据集，以及带有类描述符的Imagenet-LT版本。 Dragon在新基准测试上的表现优于最先进的模型。它也是具有类描述符（GFSL-D）和标准（仅视觉）长尾学习Imagenet-LT，CIFAR-10、100和Placs365的GFSL现有基准的新SOTA。
Real-world data is predominantly unbalanced and long-tailed, but deep models struggle to recognize rare classes in the presence of frequent classes. Often, classes can be accompanied by side information like textual descriptions, but it is not fully clear how to use them for learning with unbalanced long-tail data. Such descriptions have been mostly used in (Generalized) Zero-shot learning (ZSL), suggesting that ZSL with class descriptions may also be useful for long-tail distributions. We describe DRAGON, a late-fusion architecture for long-tail learning with class descriptors. It learns to (1) correct the bias towards head classes on a sample-by-sample basis; and (2) fuse information from class-descriptions to improve the tail-class accuracy. We also introduce new benchmarks CUB-LT, SUN-LT, AWA-LT for long-tail learning with class-descriptions, building on existing learning-with-attributes datasets and a version of Imagenet-LT with class descriptors. DRAGON outperforms state-of-the-art models on the new benchmark. It is also a new SoTA on existing benchmarks for GFSL with class descriptors (GFSL-d) and standard (vision-only) long-tailed learning ImageNet-LT, CIFAR-10, 100, and Places365.
