相关内容
Fine-tuning a deep network trained with the standard cross-entropy loss is a strong baseline for few-shot learning. When fine-tuned transductively, this outperforms the current state-of-the-art on standard datasets such as Mini-ImageNet, Tiered-ImageNet, CIFAR-FS and FC-100 with the same hyper-parameters. The simplicity of this approach enables us to demonstrate the first few-shot learning results on the ImageNet-21k dataset. We find that using a large number of meta-training classes results in high few-shot accuracies even for a large number of few-shot classes. We do not advocate our approach as the solution for few-shot learning, but simply use the results to highlight limitations of current benchmarks and few-shot protocols. We perform extensive studies on benchmark datasets to propose a metric that quantifies the "hardness" of a few-shot episode. This metric can be used to report the performance of few-shot algorithms in a more systematic way.
We are correcting some important errors and working on a new version now. Will release the updated version in the future.
Semantic segmentation is one of the basic topics in computer vision, it aims to assign semantic labels to every pixel of an image. Unbalanced semantic label distribution could have a negative influence on segmentation accuracy. In this paper, we investigate using data augmentation approach to balance the semantic label distribution in order to improve segmentation performance. We propose using generative adversarial networks (GANs) to generate realistic images for improving the performance of semantic segmentation networks. Experimental results show that the proposed method can not only improve segmentation performance on those classes with low accuracy, but also obtain 1.3% to 2.1% increase in average segmentation accuracy. It shows that this augmentation method can boost accuracy and be easily applicable to any other segmentation models.
In two-phase image segmentation, convex relaxation has allowed global minimisers to be computed for a variety of data fitting terms. Many efficient approaches exist to compute a solution quickly. However, we consider whether the nature of the data fitting in this formulation allows for reasonable assumptions to be made about the solution that can improve the computational performance further. In particular, we employ a well known dual formulation of this problem and solve the corresponding equations in a restricted domain. We present experimental results that explore the dependence of the solution on this restriction and quantify imrovements in the computational performance. This approach can be extended to analogous methods simply and could provide an efficient alternative for problems of this type.
相关VIP内容
相关资讯
![【简评】[CVPR2017]Loss Max-Pooling for Semantic Image Segmentation](https://cdn.zhuanzhi.ai/images/wx/85f9de3a9f56f199ee19af8b926e20ac!cover)
相关论文
Guneet S. Dhillon,Pratik Chaudhari,Avinash Ravichandran,Stefano Soatto
7+阅读 · 2020年3月1日
Quan Kong,Bin Tong,Martin Klinkigt,Yuki Watanabe,Naoto Akira,Tomokazu Murakami
3+阅读 · 2019年6月17日
Generative Adversarial Networks and Conditional Random Fields for Hyperspectral Image Classification
Zilong Zhong,Jonathan Li,David A. Clausi,Alexander Wong
3+阅读 · 2019年5月12日
Yuhang Cao,Kai Chen,Chen Change Loy,Dahua Lin
10+阅读 · 2019年4月9日
Juntang Zhuang
7+阅读 · 2019年4月1日
Shuangting Liu,Jiaqi Zhang,Yuxin Chen,Yifan Liu,Zengchang Qin,Tao Wan
3+阅读 · 2019年2月8日
Constantinos Papayiannis,Christine Evers,Patrick A. Naylor
4+阅读 · 2019年1月10日
Jack Spencer
3+阅读 · 2018年7月30日
Martin Rajchl,Nick Pawlowski,Daniel Rueckert,Paul M. Matthews,Ben Glocker
5+阅读 · 2018年6月11日
Duhyeon Bang,Hyunjung Shim
7+阅读 · 2018年1月28日