The goal of few-shot image recognition is to distinguish different categories with only one or a few training samples. Previous works of few-shot learning mainly work on general object images. And current solutions usually learn a global image representation from training tasks to adapt novel tasks. However, fine-gained categories are distinguished by subtle and local parts, which could not be captured by global representations effectively. This may hinder existing few-shot learning approaches from dealing with fine-gained categories well. In this work, we propose a multi-attention meta-learning (MattML) method for few-shot fine-grained image recognition (FSFGIR). Instead of using only base learner for general feature learning, the proposed meta-learning method uses attention mechanisms of the base learner and task learner to capture discriminative parts of images. The base learner is equipped with two convolutional block attention modules (CBAM) and a classifier. The two CBAM can learn diverse and informative parts. And the initial weights of classifier are attended by the task learner, which gives the classifier a task-related sensitive initialization. For adaptation, the gradient-based meta-learning approach is employed by updating the parameters of two CBAM and the attended classifier, which facilitates the updated base learner to adaptively focus on discriminative parts. We experimentally analyze the different components of our method, and experimental results on four benchmark datasets demonstrate the effectiveness and superiority of our method.

Soft robots exhibit many exciting properties due to their softness and body compliance. However, to interact with the environment safely and to perform a task effectively, a soft robot faces a series of challenges such as dexterous motion, proprioceptive sensing, and robust control of its deformable bodies. To address these issues, this article presents a method for fabrication and dynamic modeling of a novel bidirectional bending soft pneumatic actuator that embeds a curvature proprioceptive sensor. The bidirectional bending deformation was generated by two similar chambers with a sinusoidal shape for reducing the internal dampness during bending deformation. An optical waveguide made from flexible poly (methyl methacrylate) material that is immune to the inlet pressure was embedded into the actuator body to measure its bending angle. A dynamic modeling framework based on step response and parameter fitting was proposed to establish a simple differential equation that can describe the nonlinear behavior of the soft actuator. Hence, a sliding mode controller is designed based on this differential equation and the Taylor expansion. The proposed dynamical model and the sliding mode controller were validated by trajectory tracking experiments. The performance of the bidirectional bending soft actuator, such as the linear output of the curvature sensor in different inflating patterns, the proprioceptive sensitiveness to the external environment, the output force, and large bending range under relatively small pressure, was evaluated by relevant experimental paradigms. Prototypes from the novel design and fabrication process demonstrated the soft actuator's potential applications in industrial grasping and hand rehabilitation.

This study addressed whether psychopharmacologic and psychotherapeutic treatment of depressed HIV+ women met standards defined in the best practice literature, and tested hypothesized predictors of standard-concordant care. 1,352 HIV-positive women in the multi-center Women’s Interagency HIV Study were queried about depressive symptoms and mental health service utilization using standards published by the American Psychiatric Association and the Agency for Healthcare Quality and Research to define adequate depression treatment. We identified those who: 1) reported clinically significant depressive symptoms (CSDS) using Centers for Epidemiological Studies – Depression Scale (CES-D) scores of ≥ 16; or 2) had lifetime diagnoses of major depressive disorder (MDD) assessed by World Mental Health Composite International Diagnostic Interviews plus concurrent elevated depressive symptoms in the past 12 months. Adequate treatment prevalence was 46.2% (n=84) for MDD and 37.9% (n=211) for CSDS. Multivariable logistic regression analysis found that adequate treatment was more likely among women who saw the same primary care provider consistently, who had poorer role functioning, who paid out-of-pocket for healthcare, and who were not African American or Hispanic/Latina. This suggests that adequate depression treatment may be increased by promoting healthcare provider continuity, outreaching individuals with lower levels of role impairment, and addressing the specific needs and concerns of African American and Hispanic/Latina women.

No abstract