A self-supervised learning approach to deep filter banks for texture recognition
For practitioners in texture recognition facing limited data, this offers a computationally efficient alternative to transformer-based self-supervised methods.
This work proposes a self-supervised convolutional autoencoder with deep filter banks and Fisher vector pooling for texture recognition, achieving competitive accuracy with lower computational cost compared to vision transformer-based methods. On several texture databases, the method matches or exceeds state-of-the-art performance while reducing complexity.
An important challenge in texture recognition is the limited amount of data for training frequently found in real-world applications. In computer vision in general, a successful strategy to mitigate this issue is the use of a pretraining stage where the neural network learns to identify relations between parts of the data in a self-supervised manner. A well-established framework in this direction is masked autoencoder. Nevertheless, these models usually rely on computationally intensive architectures, such as vision transformers. In the particular case of texture images, most of the relevant information is compacted within a delimited area around each pixel, which suggests that capturing long-range dependence via the attention mechanism may be unnecessary. Based on that assumption, here we propose a framework where the pretraining model is a convolutional autoencoder. To leverage the rich information conveyed by texture patterns, we employ deep filters coupled with Fisher vector pooling. In this way, we improve the performance of texture recognition without adding significant computational burden. Our approach is compared with several state-of-the-art methods in different texture databases, confirming its potential both in terms of classification accuracy and computational complexity.