Can I see an Example? Active Learning the Long Tail of Attributes and Relations
Tyler L Hayes (RIT),* Maximillian Nickel (Facebook AI Research), Christopher Kanan (University of Rochester), Ludovic Denoyer (No University), Arthur Szlam (Facebook)
The 33rd British Machine Vision Conference
Abstract
There has been significant progress in creating machine learning models that identify objects in scenes along with their associated attributes and relationships; however, there is a large gap between the best models and human capabilities. One of the major reasons for this gap is the difficulty in collecting sufficient amounts of annotated relations and attributes for training these systems. While some attributes and relations are abundant, the distribution in the natural world and existing datasets is long tailed. In this paper, we address this problem by introducing a novel incremental active learning framework that asks for attributes and relations in visual scenes. While conventional active learning methods ask for labels of specific examples, we flip this framing to allow agents to ask for examples from specific categories. Using this framing, we introduce an active sampling method that asks for examples from the tail of the data distribution and show that it outperforms classical active learning methods on Visual Genome.Video
Citation
@inproceedings{Hayes_2022_BMVC,
author = {Tyler L Hayes and Maximillian Nickel and Christopher Kanan and Ludovic Denoyer and Arthur Szlam},
title = {Can I see an Example? Active Learning the Long Tail of Attributes and Relations},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0134.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by