Convolutional neural networks provide visual features that perform remarkably
well in many computer vision applications. However, training these networks
requires significant amounts of supervision. This paper introduces a generic
framework to train deep networks, end-to-end, with no supervision. We propose
to fix a set of target representations, called Noise As Targets (NAT), and to
constrain the deep features to align to them. This domain agnostic approach
avoids the standard unsupervised learning issues of trivial solutions and
collapsing of features. Thanks to a stochastic batch reassignment strategy and
a separable square loss function, it scales to millions of images. The proposed
approach produces representations that perform on par with state-of-the-art
unsupervised methods on ImageNet and Pascal VOC.

本文介绍了一种通用的框架，用于在没有监督的情况下对深度网络进行端对端训练，通过固定一组目标表示并约束其深度特征对齐到这些表示来达到目的，同时采用了随机批量重新分配策略和可分离的平方损失函数来缓解标准无监督学习中的一些问题，并且在 ImageNet 和 Pascal VOC 上能够实现与最先进的无监督方法相媲美的表现。