Abstract | ||
---|---|---|
Conducting pairwise comparisons is a widely used approach in curating human perceptual preference data. Typically raters are instructed to make their choices according to a specific set of rules that address certain dimensions of image quality and aesthetics. The outcome of this process is a dataset of sampled image pairs with their associated empirical preference probabilities. Training a model on these pairwise preferences is a common deep learning approach. However, optimizing by gradient descent through mini-batch learning means that the "global" ranking of the images is not explicitly taken into account. In other words, each step of the gradient descent relies only on a limited number of pairwise comparisons. In this work, we demonstrate that regularizing the pairwise empirical probabilities with aggregated rankwise probabilities leads to a more reliable training loss. We show that training a deep image quality assessment model with our rank-smoothed loss consistently improves the accuracy of predicting human preferences. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/ICIP40778.2020.9191231 | 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) |
DocType | ISSN | Citations |
Conference | 1522-4880 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
hossein talebi | 1 | 48 | 3.75 |
Ehsan Amid | 2 | 21 | 6.83 |
Peyman Milanfar | 3 | 3284 | 155.61 |
Manfred K. Warmuth | 4 | 6105 | 1975.48 |