arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1707.06642cs.CV
收藏

iNaturalist物种分类和检测数据集

The iNaturalist Species Classification and Detection Dataset

Caltech(加州理工学院);Google(谷歌);Cornell Tech(康奈尔科技学院);iNaturalist(iNaturalist(自然观察者)(注:此处iNaturalist为项目或平台名,根据提取规则,若为独立机构则保留,否则可能需调整,但根据原文作者归属,此处按原文提取))

Grant Van Horn, Oisin Mac Aodha, Yang Song, Yin Cui, Chen Sun, Alex Shepard, Hartwig Adam, Pietro Perona, Serge Belongie

摘要:

在计算机视觉中使用的现有图像分类数据集倾向于具有跨对象类别的图像的均匀分布。相比之下,自然界是严重不平衡的,因为一些物种比其他物种更丰富,更容易拍摄。为了鼓励在具有挑战性的现实世界条件下取得进一步进展,我们提出了iNaturalist物种分类和检测数据集,由来自5,000多种不同植物和动物的859,000张图像组成。它的特点是视觉上相似的物种,在各种各样的情况下捕捉,来自世界各地。图像是用不同类型的相机收集的,具有不同的图像质量,具有很大的类别不平衡,并已被多位公民科学家验证。我们讨论了收集的数据集,并提出了广泛的基线实验,使用最先进的计算机视觉分类和检测模型。结果表明,目前基于非集成的方法只能达到67%的前一个分类精度,说明了数据集的困难。具体来说,我们观察到训练样本数量较少的类的结果不佳,这表明在低拍摄学习中需要更多的关注。

英文摘要:

Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories. In contrast, the natural world is heavily imbalanced, as some species are more abundant and easier to photograph than others. To encourage further progress in challenging real world conditions we present the iNaturalist species classification and detection dataset, consisting of 859,000 images from over 5,000 different species of plants and animals. It features visually similar species, captured in a wide variety of situations, from all over the world. Images were collected with different camera types, have varying image quality, feature a large class imbalance, and have been verified by multiple citizen scientists. We discuss the collection of the dataset and present extensive baseline experiments using state-of-the-art computer vision classification and detection models. Results show that current non-ensemble based methods achieve only 67% top one classification accuracy, illustrating the difficulty of the dataset. Specifically, we observe poor results for classes with small numbers of training examples suggesting more attention is needed in low-shot learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑