Indexed by:会议论文
First Author:Wang,Xinggang,Wang,Xinggang
Correspondence Author:Wang,Xinggang
Co-author:Wang,Tu,Zhuowen,Liu,Wenyu,Bai,Xiang,Wang,Baoyuan
Journal:International Conference on Machine Learning (ICML), Atlanta, June, 2013
Date of Publication:2013-06-17
Abstract:Dictionary learning has became an increasingly important task in machine learning, as it is fundamental to the representation problem. A number of emerging techniques specifically include a codebook learning step, in which a critical knowledge abstraction process is carried out. Existing approaches in dictionary (codebook) learning are either generative (unsupervised e.g. k-means) or discriminative (supervised e.g. extremely randomized forests). In this paper, we propose a multiple instance learning (MIL) strategy (along the line of weakly supervised learning) for dictionary learning. Each code is represented by a classifier, such as a linear SVM, which naturally performs metric fusion for multi-channel features. We design a formulation to simultaneously learn mixtures of codes by maximizing classification margins in MIL. State-of-the-art results are observed in image classification benchmarks based on the learned codebooks, which observe both compactness and effectiveness.