图像分类与检测领域常用数据集汇总 图像分类与检测领域常用数据集 数据库 图像数目 类别数目每类图像数目图像大小(pixel)数据库论文(点击即可获取论文,如果无法下载,推荐使用SCI-HUB) MNIST60000106000 28x28 Gradient-based learning applied to document recognition CIFAR-1060000 10600032x32Learning multiple layers of features from tiny images MPEG-714007020256x256-650x600Shape descriptors for non-rigid shapes with a single closed contour15 Scenes 448515200-400约 300x250Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories Caltech-101 914610140-800约 300x200Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categoriesCaltech-256 30607256>80约 300x200Caltech-256 object category dataset PASCAL VOC 2007 9963 2096-2008 约 470x380 The PASCAL Visual Object Classes (VOC) Challenge SUN397108754 397 >100约 500x300Sun database: Large-scale scene recognition from abbey to zooSUN2012 1687382000约 500x300Sun database: Large-scale scene recognition from abbey to zoo Tiny Images7900万75062 -32x3280 million tiny images: A large data set for nonparametric object and scene recognition ImageNet-1000120万1000-约 500x400Imagenet: A large-scale hierarchical image database ImageNet 1400万10万1000 约 500x400Imagenet: A large-scale hierarchical image database 欢迎关注公众号:一刻AI 参考文献:黄凯奇, 任伟强, 谭铁牛. 图像物体分类与检测算法综述[J]. 计算机学报, 2014, 37(6): 1225-1240.