Caltech256图像数据集，256 个对象类别中的30000多张图像

The Caltech 256 is considered an improvement to its predecessor, the Caltech 101 dataset, with new features such as larger category sizes, new and larger clutter categories, and overall increased difficulty. This is a great dataset to train models for visual recognition: How can we recognize frogs, cell phones, sail boats and many other categories in cluttered pictures? How can we learn these categories in the first place? Can we endow machines with the same ability? There are 30,607 images in this dataset spanning 257 object categories. Object categories are extremely diverse, ranging from grasshopper to tuning fork. The distribution of images per category are: Original data source and banner image: http://www.vision.caltech.edu/Image_Datasets/Caltech256/ When using this dataset, please remember to cite: Griffin, G. Holub, AD. Perona, P. The Caltech 256. Caltech Technical Report.

加州理工256数据集（Caltech 256）被视为其前身加州理工101数据集（Caltech 101）的改进版本，具备多项新增特性：类别样本规模更大、新增且体量更可观的杂乱背景类别，整体任务难度亦有所提升。
该数据集是训练视觉识别模型的优质数据集：我们如何在包含杂乱背景的图像中识别青蛙、手机、帆船等众多类别？我们又该如何从零开始学习这些类别？能否赋予机器同等的视觉识别能力？
本数据集共包含30607张图像，涵盖257个物体类别。物体类别跨度极广，从蚱蜢一直延伸至音叉。
各分类的图像分布情况如下：原始数据来源与横幅图像地址：http://www.vision.caltech.edu/Image_Datasets/Caltech256/ 使用该数据集时，请务必引用以下文献：Griffin, G., Holub, A. D., Perona, P. *The Caltech 256*. Caltech 技术报告。