ST-SACLF: Style Transfer Informed Self-Attention Classifier for Bias-Aware Painting Classification

TL;DR

This paper introduces a style transfer and adaptive attention-based classifier for painting classification, significantly improving accuracy and robustness across diverse artistic styles and imbalanced datasets.

Contribution

It proposes a novel two-step approach combining style transfer with adaptive spatial attention and dynamic sample augmentation, enhancing artistic detail understanding and class balance.

Findings

Achieved 87.24% accuracy with ResNet-50 over 40 epochs.

Demonstrated effectiveness of style transfer in bridging style gaps.

Showed improved model performance through ablation and qualitative analyses.

Abstract

Painting classification plays a vital role in organizing, finding, and suggesting artwork for digital and classic art galleries. Existing methods struggle with adapting knowledge from the real world to artistic images during training, leading to poor performance when dealing with different datasets. Our innovation lies in addressing these challenges through a two-step process. First, we generate more data using Style Transfer with Adaptive Instance Normalization (AdaIN), bridging the gap between diverse styles. Then, our classifier gains a boost with feature-map adaptive spatial attention modules, improving its understanding of artistic details. Moreover, we tackle the problem of imbalanced class representation by dynamically adjusting augmented samples. Through a dual-stage process involving careful hyperparameter search and model fine-tuning, we achieve an impressive 87.24\% accuracy using the ResNet-50 backbone over 40 training epochs. Our study explores quantitative analyses that compare different pretrained backbones, investigates model optimization through ablation studies, and examines how varying augmentation levels affect model performance. Complementing this, our qualitative experiments offer valuable insights into the model's decision-making process using spatial attention and its ability to differentiate between easy and challenging samples based on confidence ranking.