Reproduce “A Comparative Survey of Vision Transformers for Feature Extraction in Texture Analysis” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Leonardo Scabini, Andre Sacilotti, Kallil M. Zielinski, Lucas C. Ribas, Bernard De Baets, Odemir M. Bruno
The authors evaluate frozen pretrained Vision Transformers as texture feature extractors, using simple classifiers across controlled and in-the-wild datasets. They compare 21 variants with ResNet50 and hand-engineered baselines, finding BeiTv2 reaches 79.1% ± 2.8 average accuracy on DTD, above ResNet50 and IFV. Results are task-dependent: on Outex13, a 3-D RGB histogram scores 94.7%, above the best ViT's 94.2%.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.