IEEE Xplore: 2017

Learning Deep Visual Object Models From Noisy Web Data: How to Make it Work

IEEE Xplore: 2017 nizarmassouh/WebDB

We contribute to this research thread with two findings: (1) a study correlating a given level of noisily labels to the expected drop in accuracy, for two deep architectures, on two different types of noise, that clearly identifies GoogLeNet as a suitable architecture for learning from Web data; (2) a recipe for the creation of Web datasets with minimal noise and maximum visual variability, based on a visual and natural language processing concept expansion strategy.