Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a self-supervised pretraining method for texture recognition using a convolutional autoencoder with deep filters and Fisher vector pooling. The approach leverages the localized nature of texture information, avoiding computationally intensive attention mechanisms. Experiments on multiple texture datasets demonstrate improved classification accuracy and reduced computational complexity compared to state-of-the-art methods.
Skip the Vision Transformers: convolutional autoencoders with deep filters and Fisher vector pooling offer a computationally efficient and accurate alternative for self-supervised texture recognition.
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.