This paper addresses flower image classification. The extent of blossom, deformation and inter-class appearance blur of flowers add great difficulties to flower classification task in addition to view, color, illumination changes that commonly occurred in other objects classification tasks. In this paper, SIFT-like feature descriptors and feature context method are used in coding local and spatial information, then LibLinear SVM classifier is employed for classification. Experimental results show that CSIFT is more robust and stable than SIFT and Dense SIFT in representing flower image. The accuracy of classification with CSIFT and feature context is comparable to state-of-the-art method. Since we do not need segment flower out of image in advance, practically, our method is better in performance and efficiency.

Supervised person re-identification (ReID) has attracted widespread attentions in the computer vision community due to its great potential in real-world applications. However, the demand of human annotation heavily limits the application as it is costly to annotate identical pedestrians appearing from different cameras. Thus, how to reduce the annotation cost while preserving the performance remains challenging and has been studied extensively. In this article, we propose a tracklet-aware co-cooperative annotators’ framework to reduce the demand of human annotation. Specifically, we partition the training samples into different clusters and associate adjacent images in each cluster to produce the robust tracklet which decreases the annotation requirements significantly. Besides, to further reduce the cost, we introduce a powerful teacher model in our framework to implement the active learning strategy and select the most informative tracklets for human annotator, the teacher model itself, in our setting, also acts as an annotator to label the relatively certain tracklets. Thus, our final model could be well-trained with both confident pseudo-labels and human-given annotations. Extensive experiments on three popular person ReID datasets demonstrate that our approach could achieve competitive performance compared with state-of-the-art methods in both active learning and unsupervised learning (USL) settings.

This study establishes a multi-source fault identification method based on a combined deep learning strategy to identify a multi-source fault effectively in the fault diagnosis of complex industrial systems. This framework is composed of feature extraction and classifier design. In the first state, the signal is transformed to the time-frequency domain and the time-frequency feature is learned using stacked denoising autoencoders. A learning method that consists of unsupervised pre-learning and supervised fine-tuning is used to train this deep model. In the second state, a model for an ensemble multiple support vector machine classifier is created to recognize fault information. Ten types of rolling bearing signals were adopted in a simulation experiment to validate the effectiveness of the proposed framework. The results demonstrate that the joint model helps to obtain higher recognition accuracy.

One-shot person Re-identification, which owns one labeled sample among numerous unlabeled data for each identity, is proposed to tackle the problem of the shortage of labeled data. Considering the scenarios without sufficient labeled data, it is very challenging to keep abreast of the performance of the supervised task in which sufficient labeled samples are available. In this paper, we propose a relation-based attention network with hybrid memory, which can make full use of the global information to pay attention to the identity features for model training with the relation-based attention network. Importantly, our specially designed network architecture effectively reduces the interference of environmental noise. Moreover, we propose a hybrid memory to train the one-shot data and unlabeled data in a unified framework, which notably contributes to the performance of person Re-identification. In particular, our designed one-shot feature update mode effectively alleviates the problem of overfitting, which is caused by the lack of supervised information during the training process. Compared with state-of-the-art unsupervised and one-shot algorithms for person Re-identification, our method achieves considerable improvements of 6.7%, 4.6%, and 11.5% on Market-1501, DukeMTMC-reID, and MSMT17 datasets, respectively, and becomes the new state-of-the-art method for one-shot person Re-identification.