图像分类,顾名思义,是一个输入图像,输出对该图像内容分类的描述的问题。它是计算机视觉的核心,实际应用广泛。

VIP内容

准确的图像和视频分类对于广泛的计算机视觉应用非常重要,从识别有害内容,到使视障人士更容易地获得产品,再到帮助人们更容易地在市场等产品上买卖东西。Facebook AI正在开发替代方法来训练我们的人工智能系统,这样我们就可以用更少的标记训练数据来做更多的事情,而且即使在无法获得大量高质量的标记数据集的情况下,也能提供准确的结果。今天,我们分享一个多功能的新模型训练技术的细节,为图像和视频分类系统提供最先进的准确性。

成为VIP会员查看完整内容
0
12

最新内容

This paper presents a hybrid approach between scale-space theory and deep learning, where a deep learning architecture is constructed by coupling parameterized scale-space operations in cascade. By sharing the learnt parameters between multiple scale channels, and by using the transformation properties of the scale-space primitives under scaling transformations, the resulting network becomes provably scale covariant. By in addition performing max pooling over the multiple scale channels, a resulting network architecture for image classification also becomes provably scale invariant. We investigate the performance of such networks on the MNISTLargeScale dataset, which contains rescaled images from original MNIST over a factor of 4 concerning training data and over a factor of 16 concerning testing data. It is demonstrated that the resulting approach allows for scale generalization, enabling good performance for classifying patterns at scales not present in the training data.

0
0
下载
预览

最新论文

This paper presents a hybrid approach between scale-space theory and deep learning, where a deep learning architecture is constructed by coupling parameterized scale-space operations in cascade. By sharing the learnt parameters between multiple scale channels, and by using the transformation properties of the scale-space primitives under scaling transformations, the resulting network becomes provably scale covariant. By in addition performing max pooling over the multiple scale channels, a resulting network architecture for image classification also becomes provably scale invariant. We investigate the performance of such networks on the MNISTLargeScale dataset, which contains rescaled images from original MNIST over a factor of 4 concerning training data and over a factor of 16 concerning testing data. It is demonstrated that the resulting approach allows for scale generalization, enabling good performance for classifying patterns at scales not present in the training data.

0
0
下载
预览
Top