This paper addresses the problem of scene classification and proposes learning discriminative and shareable patches (LDSP) method. The main idea of learning discriminative and shareable patches is to discover patches that exhibit both large between-class dissimilarity (discriminative) and large within-class similarity (shareable). A novel and efficient re-clustering, based on co-occurrence relationship of first-step clustering, is proposed and conducted to further enhance the visual similarity of patches within each cluster. In order to establish appropriate criteria for selecting desired patches, a condensed representation of image features called feature epitome is introduced. In the classification, a patch feature involving pre-trained convolutional neural network model is investigated. The experimental result outperforms existing single-feature methods on MIT 67 scene benchmark in term of mean Accuracy Precision.