Deep learning methods benefit from data sets with comprehensive coverage (e.g., ImageNet, COCO, etc.), which can be regarded as a description of the distribution of real-world data. The models trained on these datasets are considered to be able to extract general features and migrate to a domain not seen in downstream. However, in the open scene, the labeled data of the target data set are often insufficient. The depth models trained under a small amount of sample data have poor generalization ability. The identification of new categories or categories with a very small amount of sample data is still a challenging task. This paper proposes a few-shot fine-grained image recognition method. Feature maps are extracted by a CNN module with an embedded attention network to emphasize the discriminative features. A channel-based feature expression is applied to the base class and novel class followed by an improved cosine similarity-based measurement method to get the similarity score to realize the classification. Experiments are performed on main few-shot benchmark datasets to verify the efficiency and generality of our model, such as Stanford Dogs, CUB-200, and so on. The experimental results show that our method has more advanced performance on fine-grained datasets.
In this paper, two analysis models for tension leg platform (TLP) are proposed based on different simulation methods of the tendons for studying the TLP motion responses in waves. In the uncoupled analysis model, the tendon is simplified as a spring, and the restoring forces matrix is derived with the consideration of the influence of the coupled effect of horizontal offset and vertical setdown of the platform. In the coupled model, the axial and transverse vibration’s coupled effect has been considered for the establishment of the vibration equations for the tendons, and the finite difference method is used to solve the vibration equations. The time-domain coupled motion model of the platform and the mooring system is established based on the interaction forces between the tendons and the platform. The coupled and uncoupled TLP models are compared and analysed to determine their applicability. Compared with the uncoupled TLP model, the coupled TLP model has greater accuracy and a wider application range, and the effects of second-order wave force on the platform responses, horizontal offset, and vertical subsidence are analysed.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.