ECCV的全称是European Conference on Computer Vision(欧洲计算机视觉国际会议) ,两年一次,是计算机视觉三大会议(另外两个是ICCV和CVPR)之一。每次会议在全球范围录用论文300篇左右,主要的录用论文都来自美国、欧洲等顶尖实验室及研究所,中国大陆的论文数量一般在10-20篇之间。

VIP内容

针对自监督学习的深度聚类是无监督视觉表示学习中一个非常重要和有前途的方向,因为设计前置任务需要较少的领域知识。而关键组件嵌入聚类由于需要保存整个数据集的全局潜在嵌入,限制了其扩展到超大规模的数据集。在这项工作中,我们的目标是使这个框架在不降低性能的情况下更加简单和优雅。提出了一种不使用嵌入聚类的无监督图像分类框架,与标准的监督训练方法非常相似。为了进一步解释,我们进一步分析了其与深度聚类和对比学习的关系。在ImageNet数据集上进行了大量的实验,验证了该方法的有效性。此外,在迁移学习基准上的实验验证了它对其他下游任务的推广,包括多标签图像分类、目标检测、语义分割和小样本图像分类。

地址:

https://arxiv.org/abs/2006.11480

成为VIP会员查看完整内容
0
46

最新论文

Shadow removal is a computer-vision task that aims to restore the image content in shadow regions. While almost all recent shadow-removal methods require shadow-free images for training, in ECCV 2020 Le and Samaras introduces an innovative approach without this requirement by cropping patches with and without shadows from shadow images as training samples. However, it is still laborious and time-consuming to construct a large amount of such unpaired patches. In this paper, we propose a new G2R-ShadowNet which leverages shadow generation for weakly-supervised shadow removal by only using a set of shadow images and their corresponding shadow masks for training. The proposed G2R-ShadowNet consists of three sub-networks for shadow generation, shadow removal and refinement, respectively and they are jointly trained in an end-to-end fashion. In particular, the shadow generation sub-net stylises non-shadow regions to be shadow ones, leading to paired data for training the shadow-removal sub-net. Extensive experiments on the ISTD dataset and the Video Shadow Removal dataset show that the proposed G2R-ShadowNet achieves competitive performances against the current state of the arts and outperforms Le and Samaras' patch-based shadow-removal method.

0
0
下载
预览
Top