arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.01571cs.CVcs.AIcs.LG
收藏

VICRegL:局部视觉特征的自监督学习

VICRegL: Self-Supervised Learning of Local Visual Features

Meta;Inria(法国国家信息与自动化研究所);École normale supérieure(巴黎高等师范学院);CNRS(法国国家科学研究中心);PSL Research University(巴黎文理研究大学);New York University(纽约大学)

Adrien Bardes, Jean Ponce, Yann LeCun

摘要:

最近的自监督学习图像表示方法集中在产生具有不变性的全局特征,或产生一组局部特征。前者最适合分类任务,而后者最适合检测和分割任务。本文探讨了学习局部和全局特征之间的基本权衡。提出了一种名为VICRegL的新方法,该方法可以同时学习良好的全局和局部特征,在检测和分割任务上具有出色的性能,同时在分类任务上保持良好的性能。具体地说,标准卷积网络架构的两个相同分支被馈送同一图像的两个不同失真版本。VICReg准则应用于全局特征向量对。同时,VICReg准则被应用于在最后一个池化层之前出现的局部特征向量对。如果两个局部特征向量的l2距离低于阈值或者如果它们的相对位置与两个输入图像之间的已知几何变换一致,则两个局部特征向量被彼此吸引。我们在线性分类和分割传输任务上表现出强大的性能。代码和预训练模型可在以下网址公开获取:https://github.com/facebookresearch/VICRegL

英文摘要:

Most recent self-supervised methods for learning image representations focus on either producing a global feature with invariance properties, or producing a set of local features. The former works best for classification tasks while the latter is best for detection and segmentation tasks. This paper explores the fundamental trade-off between learning local and global features. A new method called VICRegL is proposed that learns good global and local features simultaneously, yielding excellent performance on detection and segmentation tasks while maintaining good performance on classification tasks. Concretely, two identical branches of a standard convolutional net architecture are fed two differently distorted versions of the same image. The VICReg criterion is applied to pairs of global feature vectors. Simultaneously, the VICReg criterion is applied to pairs of local feature vectors occurring before the last pooling layer. Two local feature vectors are attracted to each other if their l2-distance is below a threshold or if their relative locations are consistent with a known geometric transformation between the two input images. We demonstrate strong performance on linear classification and segmentation transfer tasks. Code and pretrained models are publicly available at: https://github.com/facebookresearch/VICRegL

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。

↑