How hard can it be? Estimating the difficulty of visual search in an image

Radu Tudor Ionescu, Bogdan Alexe, Marius Leordeanu, Dim P. Papadopoulos, Vittorio Ferrari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

We address the problem of estimating image difficulty de-fined as the human response time for solving a visual search task. We collect human annotations of image difficulty for the PASCAL VOC 2012 data set through a crowd-sourcing platform. We then analyze what human interpretable image properties can have an impact on visual search difficulty, and how accurate are those properties for predicting difficulty. Next, we build a regression model based on deep features learned with state of the art convolutional neural networks and show better results for predicting the ground truth visual search difficulty scores produced by human annotators. Our model is able to correctly rank about 75% image pairs according to their difficulty score. We also show that our difficulty predictor generalizes well to new classes not seen during training. Finally, we demonstrate that our predicted difficulty scores are useful for weakly supervised object localization (8% improvement) and semi-supervised object classification (1% improvement).
Original languageEnglish
Title of host publicationComputer Vision and Pattern Recognition (CVPR), 2016 IEEE Conference on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages10
ISBN (Electronic)978-1-4673-8851-1
ISBN (Print)978-1-4673-8852-8
Publication statusPublished - 12 Dec 2016
Event29th IEEE Conference on Computer Vision and Pattern Recognition - Las Vegas, United States
Duration: 26 Jun 20161 Jul 2016


Conference29th IEEE Conference on Computer Vision and Pattern Recognition
Abbreviated titleCVPR 2016
Country/TerritoryUnited States
CityLas Vegas
Internet address


Dive into the research topics of 'How hard can it be? Estimating the difficulty of visual search in an image'. Together they form a unique fingerprint.

Cite this