论文标题
使用班级均衡专家的长尾识别
Long-Tailed Recognition Using Class-Balanced Experts
论文作者
论文摘要
深度学习可以使用大规模的人工平衡数据集在图像识别中令人印象深刻的表现。但是，现实世界中的数据集表现出高度的级别不平衡分布，提出了两个主要挑战：中等事物或几乎没有照片类别的类别和数据稀缺之间的相对失衡。在这项工作中，我们解决了长尾识别的问题，其中训练集高度不平衡，并且测试集保持平衡。与现有范式不同的范式依赖于数据的范例，依赖数据映射，成本敏感的学习，在线硬采矿，损失目标重塑和/或基于内存的建模，我们提出了一组平衡的专家，以结合各种分类器的力量。我们的班级平衡专家合奏达到了最先进的成绩，并且扩展的合奏在两个基准上建立了新的最先进的基准，以进行长尾识别。我们进行了广泛的实验来分析合奏的性能，并发现在现代的大规模数据集中，相对失衡比数据稀缺更难。培训和评估代码可从https://github.com/ssfootball04/class-balanced-experts获得。
Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced distributions, yielding two main challenges: relative imbalance amongst the classes and data scarcity for mediumshot or fewshot classes. In this work, we address the problem of long-tailed recognition wherein the training set is highly imbalanced and the test set is kept balanced. Differently from existing paradigms relying on data-resampling, cost-sensitive learning, online hard example mining, loss objective reshaping, and/or memory-based modeling, we propose an ensemble of class-balanced experts that combines the strength of diverse classifiers. Our ensemble of class-balanced experts reaches results close to state-of-the-art and an extended ensemble establishes a new state-of-the-art on two benchmarks for long-tailed recognition. We conduct extensive experiments to analyse the performance of the ensembles, and discover that in modern large-scale datasets, relative imbalance is a harder problem than data scarcity. The training and evaluation code is available at https://github.com/ssfootball04/class-balanced-experts.
