arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.09458cs.CVcs.LG
收藏

动态Few-Shot视觉学习

Dynamic Few-Shot Visual Learning without Forgetting

University Paris-Est(巴黎东部大学);LIGM(法国国立路桥学校计算机科学实验室);Ecole des Ponts ParisTech(法国国立路桥学校)

Spyros Gidaris, Nikos Komodakis

摘要:

人类的视觉系统有一种惊人的能力,能够毫不费力地从几个例子中学习新的概念。在机器学习视觉系统上模仿相同的行为是一个有趣且非常具有挑战性的研究问题,在现实世界的视觉应用中具有许多实际优势。在这种情况下,我们的工作的目标是设计一个Few-Shot视觉学习系统,在测试期间,它将能够有效地学习新的类别,从只有几个训练数据,而在同一时间,它不会忘记它被训练的初始类别(这里称为基本类别)。为了实现这一目标,我们建议(a)扩展一个对象识别系统的注意力为基础的Few-Shot分类权重生成器,和(b)重新设计的分类器的ConvNet模型之间的特征表示和分类权重向量的余弦相似性函数。后者,除了统一识别的新类别和基本类别,它也导致了功能表示,更好地概括“看不见”的类别。我们在Mini-ImageNet上对我们的方法进行了广泛的评估,在Mini-ImageNet上,我们设法改进了现有的Few-Shot识别技术(即,我们在1次和5次设置上分别实现了56.20%和73.00%),而同时我们没有牺牲基本类别上的任何准确性,这是大多数现有方法所缺乏的特性。最后,我们将我们的方法应用于最近引入的Bharath和Girshick [4]的Few-Shot基准,在那里我们也获得了最先进的结果。我们论文的代码和模型将发布在:https://github.com/gidariss/FewShotWithoutForgetting

英文摘要:

The human visual system has the remarkably ability to be able to effortlessly learn novel concepts from only a few examples. Mimicking the same behavior on machine learning vision systems is an interesting and very challenging research problem with many practical advantages on real world vision applications. In this context, the goal of our work is to devise a few-shot visual learning system that during test time it will be able to efficiently learn novel categories from only a few training data while at the same time it will not forget the initial categories on which it was trained (here called base categories). To achieve that goal we propose (a) to extend an object recognition system with an attention based few-shot classification weight generator, and (b) to redesign the classifier of a ConvNet model as the cosine similarity function between feature representations and classification weight vectors. The latter, apart from unifying the recognition of both novel and base categories, it also leads to feature representations that generalize better on "unseen" categories. We extensively evaluate our approach on Mini-ImageNet where we manage to improve the prior state-of-the-art on few-shot recognition (i.e., we achieve 56.20% and 73.00% on the 1-shot and 5-shot settings respectively) while at the same time we do not sacrifice any accuracy on the base categories, which is a characteristic that most prior approaches lack. Finally, we apply our approach on the recently introduced few-shot benchmark of Bharath and Girshick [4] where we also achieve state-of-the-art results. The code and models of our paper will be published on: https://github.com/gidariss/FewShotWithoutForgetting

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。

↑