Fine-grained few-shot learning is a difficult task in image classification. The reason is that the discriminative
features of fine-grained images are often located in local areas of the image, while most of the existing few-shotlearning image classification methods only use top-level features and adopt a single measure. In that way, the localfeatures of the sample cannot be learned well. In response to this problem, ensemble relation network with multi-level measure (ERN-MM) is proposed in this paper. It adds the relation modules in the shallow feature space tocompare the similarity between the samples in the local features, and finally integrates the similarity scores from thefeature spaces to assign the label of the query samples. So the proposed method ERN-MM can use local details andglobal information of different grains. Experimental results on different fine-grained datasets show that the proposedmethod achieves good classification performance and also proves its rationality. 相似文献
Detection-based pedestrian counting methods produce results of considerable accuracy in non-crowded scenes. However, the detection-based approach is dependent on the camera viewpoint. On the other hand, map-based pedestrian counting methods are performed by measuring features that do not require separate detection of each pedestrian in the scene. Thus, these methods are more effective especially in high crowd density. In this paper, we propose a hybrid map-based model that is a new directional pedestrian counting model. Our proposed model is composed of direction estimation module with classified foreground motion vectors, and pedestrian counting module with principal component analysis. Our contributions in this paper have two aspects. First, we present a directional moving pedestrian counting system that does not depend on object detection or tracking. Second, the number and major directions of pedestrian movements can be detected, by classifying foreground motion vectors. This representation is more powerful than simple features in terms of handling noise, and can count the moving pedestrians in images more accurately.
An improved morphological component analysis (MCA) method is proposed for the compound fault diagnosis of gearboxes. When gear fault and bearing fault occur simultaneously, the compound fault signal of the gearbox contains meshing components (related to the gear fault) and periodic impulse components (related to the bearing fault). The corresponding fault characteristics can be separated by MCA according to the morphological differences of the components. In the proposed method, the optimal dictionary, which can represent the characteristics of bearing faults, is first selected based on the principle of minimum information entropy. Then, the compound fault signal is decomposed into the meshing component and the periodic impulse component using MCA. Finally, the separated components are subjected to the Hilbert envelope spectrum analysis. The faults of the gear and the bearing can be diagnosed according to the envelope spectra of the separated fault signal components. Simulation and experimental studies validate the effectiveness of the proposed method for the compound fault diagnosis of gearboxes. 相似文献