17 citations
4 papers
It Takes Two to Tango: Mixup for Deep Metric Learning
Shashanka Venkataramanan, Bill Psomas, Ewa Kijak +3
Metric learning involves learning a discriminative representation such that embeddings of similar classes are encouraged to be close, while embeddings of dissimilar classes are pus…
Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images
Zhaohui Yang, Miaojing Shi, Chao Xu +2
Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire trainin…
Homo Cyberneticus: The Era of Human-AI Integration
Jun Rekimoto
This article is submitted and accepted as ACM UIST 2019 Visions. UIST Visions is a venue for forward thinking ideas to inspire the community. The goal is not to report research but…
Graph convolutional networks for learning with few clean and many noisy labels
Ahmet Iscen, Giorgos Tolias, Yannis Avrithis +2
In this work we consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given. The structure of clean and noisy data is modeled by a g…