← Search

Dengke Dong

2 accepted papers

2019

Multi-Similarity Loss With General Pair Weighting for Deep Metric Learning

CVPR 2019poster

A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad of solutions for deep metric learning. In this pa-per, we provide a general weighting framework for under-standing recent pair-based loss functions. Our contributions are t…

Cited by 1000PDFcodeScholar
2018

CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images

ECCV 2018poster

We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled rawly from the Internet by using text queries, without any human annotation. We develop a principled learning strategy by leveraging curriculum learning,…