Few-shot learning in image classification aims to learn a classifier to classify images when only few training examples are available for each class. Recent work has achieved promising classification performance, where an image-level feature based measure is usually used. In this paper, we argue that a measure at such a level may not be effective enough in light of the scarcity of examples in few-shot learning. Instead, we think a local descriptor based image-to-class measure should be taken, inspired by its surprising success in the heydays of local invariant features. Specifically, building upon the recent episodic training mechanism, we propose a Deep Nearest Neighbor Neural Network (DN4 in short) and train it in an end-to-end manner. Its key difference from the literature is the replacement of the image-level feature based measure in the final layer by a local descriptor based image-to-class measure. This measure is conducted online via a k-nearest neighbor search over the deep local descriptors of convolutional feature maps. The proposed DN4 not only learns the optimal deep local descriptors for the image-to-class measure, but also utilizes the higher efficiency of such a measure in the case of example scarcity, thanks to the exchangeability of visual patterns across the images in the same class. Our work leads to a simple, effective, and computationally efficient framework for few-shot learning. Experimental study on benchmark datasets consistently shows its superiority over the related stateof-the-art, with the largest absolute improvement of 17% over the next best. The source code can be available from https://github.com/WenbinLee/DN4.git.

Pretreatment ADC histogram analysis can stratify progression-free survival in bevacizumab-treated patients with recurrent GBM.

Few-shot learning aims to recognize new concepts from very few examples. However, most of the existing few-shot learning methods mainly concentrate on the first-order statistic of concept representation or a fixed metric on the relation between a sample and a concept. In this work, we propose a novel end-to-end deep architecture, named Covariance Metric Networks (CovaMNet). The CovaMNet is designed to exploit both the covariance representation and covariance metric based on the distribution consistency for the few-shot classification tasks. Specifically, we construct an embedded local covariance representation to extract the second-order statistic information of each concept and describe the underlying distribution of this concept. Upon the covariance representation, we further define a new deep covariance metric to measure the consistency of distributions between query samples and new concepts. Furthermore, we employ the episodic training mechanism to train the entire network in an end-to-end manner from scratch. Extensive experiments in two tasks, generic few-shot image classification and fine-grained fewshot image classification, demonstrate the superiority of the proposed CovaMNet. The source code can be available from https://github.com/WenbinLee/CovaMNet.git.

Descending signals from the brain play critical roles in controlling and modulating locomotion kinematics. In the nervous system, descending AVB premotor interneurons exclusively form gap junctions with the B-type motor neurons that execute forward locomotion. We combined genetic analysis, optogenetic manipulation, calcium imaging, and computational modeling to elucidate the function of AVB-B gap junctions during forward locomotion. First, we found that some B-type motor neurons generate rhythmic activity, constituting distributed oscillators. Second, AVB premotor interneurons use their electric inputs to drive bifurcation of B-type motor neuron dynamics, triggering their transition from stationary to oscillatory activity. Third, proprioceptive couplings between neighboring B-type motor neurons entrain the frequency of body oscillators, forcing coherent bending wave propagation. Despite substantial anatomical differences between the motor circuits of and higher model organisms, converging principles govern coordinated locomotion.