Authors
- William Thong
- Jose Costa Pereira*
- Sarah Parisot*
- Ales Leonardis*
- Steven McDonagh*
* External authors
Venue
- BMVC 2022
Date
- 2022
Share
Content-Diverse Comparisons improve IQA
Jose Costa Pereira*
Sarah Parisot*
Ales Leonardis*
Steven McDonagh*
* External authors
BMVC 2022
2022
Abstract
Image quality assessment (IQA) forms a natural and often straightforward undertaking for humans, yet effective automation of the task remains highly challenging. Recent metrics from the deep learning community commonly compare image pairs during training to improve upon traditional metrics such as PSNR or SSIM. However, current comparisons ignore the fact that image content affects quality assessment as comparisons only occur between images of similar content. This restricts the diversity and number of image pairs that the model is exposed to during training. In this paper, we strive to enrich these comparisons with content diversity. Firstly, we relax comparison constraints, and compare pairs of images with differing content. This increases the variety of available comparisons. Secondly, we introduce listwise comparisons to provide a holistic view to the model. By including differentiable regularizers, derived from correlation coefficients, models can better adjust predicted scores relative to one another. Evaluation on multiple benchmarks, covering a wide range of distortions and image content, shows the effectiveness of our learning scheme for training image quality assessment models.
Related Publications
Human-centric computer vision (HCCV) data curation practices often neglect privacy and bias concerns, leading to dataset retractions and unfair models. HCCV datasets constructed through nonconsensual web scraping lack crucial metadata for comprehensive fairness and robustnes…
This paper considers retrieval of videos containing human activity from just a video query. In the literature, a common assumption is that all activities have sufficient labelled examples when learning an embedding for retrieval. However, this assumption does not hold in pra…
This paper strives to measure apparent skin color in computer vision, beyond a unidimensional scale on skin tone. In their seminal paper Gender Shades, Buolamwini and Gebru have shown how gender classification systems can be biased against women with darker skin tones. While…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.
