论文标题
一个自制的gan，用于无监督的几个对象识别
A Self-supervised GAN for Unsupervised Few-shot Object Recognition
论文作者
论文摘要
本文讨论了无监督的几个对象识别，其中所有训练图像均未标记，并且测试图像分为查询，每个对象类别的兴趣类别都标有一些标记的支持图像。培训和测试图像不共享对象类。我们通过两个损失功能扩展了香草甘，均针对自学学习。第一个是重建损失，该损失可以强制歧视器重建概率采样的潜在代码，该代码用于生成“假”图像。第二个是三胞胎损失，该损失可以强制执行歧视器来输出图像编码，这些图像对更接近的图像进行了更接近。评估，比较和详细的消融研究是在几乎没有分类的背景下进行的。我们的方法极大地超过了迷你象征和分层imagenet数据集的艺术状态。
This paper addresses unsupervised few-shot object recognition, where all training images are unlabeled, and test images are divided into queries and a few labeled support images per object class of interest. The training and test images do not share object classes. We extend the vanilla GAN with two loss functions, both aimed at self-supervised learning. The first is a reconstruction loss that enforces the discriminator to reconstruct the probabilistically sampled latent code which has been used for generating the "fake" image. The second is a triplet loss that enforces the discriminator to output image encodings that are closer for more similar images. Evaluation, comparisons, and detailed ablation studies are done in the context of few-shot classification. Our approach significantly outperforms the state of the art on the Mini-Imagenet and Tiered-Imagenet datasets.
