Unbiased Look at Dataset Bias

10 years 1 months ago
Unbiased Look at Dataset Bias
Datasets are an integral part of contemporary object recognition research. They have been the chief reason for the considerable progress in the field, not just as source of large amounts of training data, but also as means of measuring and comparing performance of competing algorithms. At the same time, datasets have often been blamed for narrowing the focus of object recognition research, reducing it to a single benchmark performance number. Indeed, some datasets, that started out as data capture efforts aimed at representing the visual world, have become closed worlds unto themselves (e.g. the Corel world, the Caltech101 world, the PASCAL VOC world). With the focus on beating the latest benchmark numbers on the latest dataset, have we perhaps lost sight of the original purpose? The goal of this paper is to take stock of the current state of recognition datasets. We present a comparison study using a set of popular datasets, evaluated based on a number of criteria including: relativ...
Antonio Torralba, Alyosha Efros
Added 30 Apr 2011
Updated 30 Apr 2011
Type Journal
Year 2011
Where CVPR
Authors Antonio Torralba, Alyosha Efros
Comments (0)