|
KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment| old_uid | 16152 |
|---|
| title | KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment |
|---|
| start_date | 2018/07/06 |
|---|
| schedule | 14h-15h |
|---|
| online | no |
|---|
| location_info | salle D005 |
|---|
| summary | This talk is about building a large and diverse image quality database via crowdsourcing, and introducing a deep learning approach that can make best use of it. The main challenge in applying state-of-the-art deep learning methods to predict image quality in-the-wild is the relatively small size of existing quality scored datasets. The reason for the lack of larger datasets is the massive resources required in generating diverse and publishable content. We present a new systematic and scalable approach to create large-scale, authentic and diverse image datasets for Image Quality Assessment (IQA). We show how we built an IQA database, KonIQ-10k, consisting of 10,073 images, on which we performed very large scale crowdsourcing experiments in order to obtain reliable quality ratings from 1,467 crowd workers (1.2 million ratings). We argue for its ecological validity by analyzing the diversity of the dataset, by comparing it to state-of-the-art IQA databases, and by checking the reliability of our user studies. Our novel BIQA method is based on deep learning with convolutional neural networks (CNN); it is trained on full and arbitrarily sized images rather than small image patches or resized input images as usually done in CNNs for image classification and quality assessment. The resolution independence is achieved by pyramid pooling. This work is the first that applies a fine-tuned residual deep learning network (ResNet-101) to BIQA. In contrast to previous methods we do not train to approximate the MOS directly, but rather use the distributions of scores. Experiments were carried out on three benchmark image quality databases. The results showed clear improvements of the accuracy of the estimated MOS values, compared to current state-of-the-art algorithms. |
|---|
| responsibles | Brière |
|---|
| |
|