Pseudo-labelling and Meta Reweighting Learning for Image Aesthetic Quality Assessment

TL;DR

This paper introduces a novel approach for image aesthetic quality assessment using a mixed dataset, meta reweighting, pseudo-labeling, and adaptive network structures, significantly improving evaluation accuracy.

Contribution

It proposes a new AMD-CR dataset, a meta reweighting network, and an adaptive aesthetic block, advancing the accuracy and robustness of aesthetic quality evaluation methods.

Findings

Improved SROCC by 0.1112 over conventional methods.

Effective pseudo-labeling enhances training in classification and regression.

Adaptive network structures handle variable input sizes efficiently.

Abstract

In the tasks of image aesthetic quality evaluation, it is difficult to reach both the high score area and low score area due to the normal distribution of aesthetic datasets. To reduce the error in labeling and solve the problem of normal data distribution, we propose a new aesthetic mixed dataset with classification and regression called AMD-CR, and we train a meta reweighting network to reweight the loss of training data differently. In addition, we provide a training strategy acccording to different stages, based on pseudo labels of the binary classification task, and then we use it for aesthetic training acccording to different stages in classification and regression tasks. In the construction of the network structure, we construct an aesthetic adaptive block (AAB) structure that can adapt to any size of the input images. Besides, we also use the efficient channel attention (ECA) to strengthen the feature extracting ability of each task. The experimental result shows that our method improves 0.1112 compared with the conventional methods in SROCC. The method can also help to find best aesthetic path planning for unmanned aerial vehicles (UAV) and vehicles.