Semantic Scholar Open Access 2019 166 sitasi

Effective Aesthetics Prediction With Multi-Level Spatially Pooled Features

Vlad Hosu Bastian Goldlücke D. Saupe

Lihat Sumber DOI

Abstrak

We propose an effective deep learning approach to aesthetics quality assessment that relies on a new type of pre-trained features, and apply it to the AVA data set, the currently largest aesthetics database. While previous approaches miss some of the information in the original images, due to taking small crops, down-scaling or warping the originals during training, we propose the first method that efficiently supports full resolution images as an input, and can be trained on variable input sizes. This allows us to significantly improve upon the state of the art, increasing the Spearman rank-order correlation coefficient (SRCC) of ground-truth mean opinion scores (MOS) from the existing best reported of 0.612 to 0.756. To achieve this performance, we extract multi-level spatially pooled (MLSP) features from all convolutional blocks of a pre-trained InceptionResNet-v2 network, and train a custom shallow Convolutional Neural Network (CNN) architecture on these new features.

Topik & Kata Kunci

Computer Science

Penulis (3)

Vlad Hosu

Bastian Goldlücke

D. Saupe

Format Sitasi

APA MLA BibTeX

Hosu, V., Goldlücke, B., Saupe, D. (2019). Effective Aesthetics Prediction With Multi-Level Spatially Pooled Features. https://doi.org/10.1109/cvpr.2019.00960

Akses Cepat

Lihat di Sumber doi.org/10.1109/cvpr.2019.00960

Informasi Jurnal

Tahun Terbit: 2019
Bahasa: en
Total Sitasi: 166×
Sumber Database: Semantic Scholar
DOI: 10.1109/cvpr.2019.00960
Akses: Open Access ✓