Details

Autor(en) / Beteiligte

• Hang Zhang
• Jia Xue
• Dana, Kristin

Titel

Deep TEN: Texture Encoding Network

Ist Teil von

• 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, p.2896-2905

Ort / Verlag

IEEE

Erscheinungsjahr

2017

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• We propose a Deep Texture Encoding Network (Deep-TEN) with a novel Encoding Layer integrated on top of convolutional layers, which ports the entire dictionary learning and encoding pipeline into a single model. Current methods build from distinct components, using standard encoders with separate off-the-shelf features such as SIFT descriptors or pre-trained CNN features for material recognition. Our new approach provides an end-to-end learning framework, where the inherent visual vocabularies are learned directly from the loss function. The features, dictionaries, encoding representation and the classifier are all learned simultaneously. The representation is orderless and therefore is particularly useful for material and texture recognition. The Encoding Layer generalizes robust residual encoders such as VLAD and Fisher Vectors, and has the property of discarding domain specific information which makes the learned convolutional features easier to transfer. Additionally, joint training using multiple datasets of varied sizes and class labels is supported resulting in increased recognition performance. The experimental results show superior performance as compared to state-of-the-art methods using gold-standard databases such as MINC-2500, Flickr Material Database, KTH-TIPS-2b, and two recent databases 4D-Light-Field-Material and GTOS. The source code for the complete system are publicly available1.