RADAM: Texture recognition through randomized aggregated encoding of deep activation maps
Leonardo Scabini, Kallil M. Zielinski, Lucas C. Ribas, Wesley Nunes Gonçalves, Bernard De Baets, Odemir Martinez Bruno
Abstract
Texture analysis is a classical yet challenging task in computer vision for which deep neural networks are actively being applied. Most approaches are based on building feature aggregation modules around a pre-trained backbone and then fine-tuning the new architecture on specific texture recognition tasks. Here we propose a new method named R andom encoding of A ggregated D eep A ctivation M aps (RADAM) which extracts rich texture representations without ever changing the backbone. The technique consists of encoding the output at different depths of a pre-trained deep convolutional network using a Randomized Autoencoder (RAE). The RAE is trained locally to each image using a closed-form solution, and its decoder weights are used to compose a 1-dimensional texture representation that is fed into a linear SVM . This means that no fine-tuning or backpropagation is needed for the backbone. We explore RADAM on several texture benchmarks and achieve state-of-the-art results with different computational budgets. Our results suggest that pre-trained backbones may not require additional fine-tuning for texture recognition if their learned representations are better encoded.