Weight-aware Semi-Supervised Self-ensembling Framework for Interior Decoration Style Classification

Lichun Guo^1*Hao Zeng¹Junliang Wang²Shuang Liang³Wenlong Hang⁴

• ¹College of Art and Design, Nanjing Audit University Jinshen College, Nanjing, China
• ²College of Computer and Information Engineering, Nanjing Tech University, Nanjing, China
• ³School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China
• ⁴Nanjing Tech University, Nanjing, China

Automatic classification of interior decoration styles has great potential to guide and streamline the design process. Despite recent advancements, it remains challenging to construct an accurate interior decoration style recognition model due to the scarcity of expert annotations. In this paper, we develop a new weight-aware semisupervised self-ensembling framework for interior decoration style recognition, which selectively leverages the abundant unlabeled data to address the aforementioned challenge. Specifically, we devise a weight module that utilizes a truncated Gaussian function to automatically assess the reliability of unlabeled data. This enables more reliable unlabeled samples to be adaptively assigned higher weights during the training process. By incorporating adaptive weights, we devise a weighted consistency regularization to enforce consistent predictions for reliable unlabeled data under different perturbations. Furthermore, we devise a weighted relation consistency regularization to preserve the semantic relationships of reliable unlabeled data across various perturbations. Additionally, we introduce a weighted class-aware contrastive learning regularization to improve the model's discriminative feature learning capability using reliable unlabeled data. The synergistic learning of weighted consistency regularization, weighted relation consistency, and weighted class-aware contrastive learning significantly enhances the model's generalizability. Extensive experiments conducted on interior decoration style image datasets demonstrate the superior performance of our framework compared to existing semi-supervised learning methods.