VORTEX: challenging CNNs at texture recognition by using vision transformers with orderless and randomized token encodings.
SCABINI, Leonardo Felipe dos Santos; ZIELINSKI, Kallil Miguel Caparroz; KONUK, Emir; FARES, Ricardo Trivizan; RIBAS, Lucas Correia; SMITH, Kevin; BRUNO, Odemir Martinez.
SCABINI, Leonardo Felipe dos Santos; ZIELINSKI, Kallil Miguel Caparroz; KONUK, Emir; FARES, Ricardo Trivizan; RIBAS, Lucas Correia; SMITH, Kevin; BRUNO, Odemir Martinez.
Abstract: Texture recognition has recently been dominated by ImageNet-pre-trained deep Convolutional Neural Networks (CNNs), with specialized modifications and feature engineering required to achieve state-of-the-art (SOTA) performance. However, although Vision Transformers (ViTs) were introduced a few years ago, little is known about their texture recognition abilities. Therefore, in this work, we introduce VORTEX (ViTs with Orderless and Randomized Token Encodings for Texture Recognition), a novel method that enables the effective use of ViTs for texture analysis. VORTEX extracts multi-depth token embeddings from pre-trained ViT backbones and employs a lightweight module to aggregate hierarchical features and perform orderless encoding, obtaining a better image representation for texture recognition tasks. This approach allows seamless integration with any ViT using the common transformer architecture. Moreover, no fine-tuning of the backbone is performed, as they are used only as frozen feature extractors, and the features are fed to a linear SVM. We evaluate VORTEX on nine diverse texture datasets, demonstrating its ability to achieve or surpass SOTA performance in a variety of texture analysis scenarios. By bridging the gap between texture recognition with CNNs and transformer-based architectures, VORTEX paves the way for adopting emerging transformer foundation models. Furthermore, VORTEX demonstrates robust computational efficiency when coupled with ViT backbones compared to CNNs with similar costs. The method implementation and experimental scripts are publicly available in our online repository (https://github.com/scabini/VORTEX).
@article={003305424,author = {SCABINI, Leonardo Felipe dos Santos; ZIELINSKI, Kallil Miguel Caparroz; KONUK, Emir; FARES, Ricardo Trivizan; RIBAS, Lucas Correia; SMITH, Kevin; BRUNO, Odemir Martinez.},title={VORTEX: challenging CNNs at texture recognition by using vision transformers with orderless and randomized token encodings},journal={Neurocomputing},note={v. 693, p. 133852-1-133852-14},year={2026}}