Integrating Deep Features For Material Recognition
2016 23rd International Conference on Pattern Recognition (ICPR)(2016)
摘要
This paper considers the problem of material recognition. Motivated by observation of close interconnections between material and object recognition, we study how to select and integrate multiple features obtained by different models of Convolutional Neural Networks (CNNs) trained in a transfer learning setting. To be specific, we first compute activations of features using representations on images to select a set of samples which are best represented by the features. Then, we measure uncertainty of the features by computing entropy of class distributions for each sample set. Finally, we compute contribution of each feature to representation of classes for feature selection and integration. Experimental results show that the proposed method achieves state-of-the-art performance on two benchmark datasets for material recognition. Additionally, we introduce a new material dataset, named EFMD, which extends Flickr Material Database (FMD). By the employment of the EFMD for transfer learning, we achieve 84.0% +/- 1.8% accuracy on the FMD dataset, which is close to the reported human performance 84.9%.
更多查看译文
关键词
deep feature integration,material recognition,object recognition,convolutional neural networks,CNNs,transfer learning,image representations,class distribution entropy,feature selection,EFMD material dataset,Flickr material database
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络