Select Language

公开数据集

斯坦福大学-犬类数据集

斯坦福大学-犬类数据集

Scene:

Animal

Data Type:

2D Box,Image Caption
所需积分:15 去赚积分?
  • 1327浏览
  • 195下载
  • 3点赞
  • 收藏
  • 分享

贡献者查看主页

Stanford University

A place for learning, discovery, innovation, expression and discourse

Data Preview ? 756.8M

    Data Structure ?

    *数据结构实际以真实数据为准

    The Stanford Dogs dataset contains images of 120 breeds of dogs from around the world. This dataset has been built using images and annotation from ImageNet for the task of fine-grained image categorization. Contents of this dataset:

        1.Number of categories: 120
        2.Number of images: 20,580
        3.Annotations: Class labels, Bounding boxes

    Dataset ReferencePrimary:
      Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao and Li Fei-Fei. Novel dataset for Fine-Grained Image Categorization. First Workshop on Fine-Grained Visual Categorization (FGVC), IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.  [pdf]  [poster]  [BibTex]
    Secondary:
      J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li and L. Fei-Fei, ImageNet: A Large-Scale Hierarchical Image Database. IEEE Computer Vision and Pattern Recognition (CVPR), 2009.  [pdf]  [BibTex]

    baseline Results
    This section contains baseline results on two tasks:

      Mean Accuracy
    The number of training images per class is varied from 1 to 100.
      Comparison of Accuracy per Class
    The accuracy of each class is compared for 15 and 100 training images per class.



    Experimental Setting
    All of the experiments use image regions from the bounding box only for both training and testing.
    The remaining parameters are set to the following values:

    Contact:

    Aditya Khosla、Nityananda、Jayadevaprakash、Bangpeng Yao、Li Fei-Fei

    aditya86@cs.stanford.edu
    bangpeng@cs.stanford.edu



    0相关评论
    ×

    帕依提提提温馨提示

    该数据集正在整理中,为您准备了其他渠道,请您使用

    注:部分数据正在处理中,未能直接提供下载,还请大家理解和支持。