Effective Aesthetics Prediction with Multi-level Spatially Pooled Features

04/02/2019
by   Vlad Hosu, et al.
0

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.

READ FULL TEXT

page 4

page 8

research
01/20/2020

DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning

Multi-level deep-features have been driving state-of-the-art methods for...
research
12/17/2019

No-Reference Video Quality Assessment using Multi-Level Spatially Pooled Features

Video Quality Assessment (VQA) methods have been designed with a focus o...
research
07/14/2020

MFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering

In this paper, we propose a novel convolutional neural network (CNN) arc...
research
05/24/2018

Environmental Sound Classification Based on Multi-temporal Resolution Convolutional Neural Network Combining with Multi-level Features

Motivated by the fact that characteristics of different sound classes ar...
research
11/10/2020

Multi-pooled Inception features for no-reference image quality assessment

Image quality assessment (IQA) is an important element of a broad spectr...
research
07/29/2022

Rating the Crisis of Online Public Opinion Using a Multi-Level Index System

Online public opinion usually spreads rapidly and widely, thus a small i...

Please sign up or login with your details

Forgot password? Click here to reset