Undoing the Damage of Dataset Bias

The presence of bias in existing object recognition datasets is now well-known in the computer vision community. While it remains in question whether creating an unbiased dataset is possible given limited resources, in this work we propose a discriminative framework that directly exploits dataset bi...

Cijeli opis

Bibliografski detalji
Glavni autor: Khosla, Aditya
Daljnji autori: Massachusetts Institute of Technology. Media Laboratory
Format: Članak
Jezik:English
Izdano: Springer Nature 2019
Online pristup:https://hdl.handle.net/1721.1/122669