Training deep retrieval models with noisy datasets: Bag exponential loss
作者：
Highlights：
• A noise-robust loss based on Multiple Instance Learning (MIL) is used to train CNNs for retrieval under noisy datasets.
• The Bag Exponential (BE) presented is flexible enough to be used for other purposes than dealing with noise, such as online hard positive mining.
• Our method allows to use noisy generated training sets, which are easy and quick to create, to adapt CNNs for image retrieval on any new object.
摘要
•A noise-robust loss based on Multiple Instance Learning (MIL) is used to train CNNs for retrieval under noisy datasets.•The Bag Exponential (BE) presented is flexible enough to be used for other purposes than dealing with noise, such as online hard positive mining.•Our method allows to use noisy generated training sets, which are easy and quick to create, to adapt CNNs for image retrieval on any new object.
论文关键词：Image retrieval,Noise,Multiple instance learning,Loss functions
论文评审过程：Received 29 May 2020, Revised 19 November 2020, Accepted 29 December 2020, Available online 1 January 2021, Version of Record 6 January 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107811
