Few-shot learning has received increasing attention and witnessed significant advances in recent years. However, most of the few-shot learning methods focus on the optimization of training process, and the learning of metric and sample generating networks. They ignore the importance of learning the ground-truth feature distributions of few-shot classes. This paper proposes a direction-driven weighting method to make the feature distributions of few-shot classes precisely fit the ground-truth distributions. The learned feature distributions can generate an unlimited number of training samples for the few-shot classes to avoid overfitting. Specifically, the proposed method consists of two optimization strategies. The direction-driven strategy is for capturing more complete direction information that can describe the feature distributions. The similarity-weighting strategy is proposed to estimate the impact of different classes in the fitting procedure and assign corresponding weights. Our method outperforms the current state-of-the-art performance by an average of 3% for 1-shot on standard few-shot learning benchmarks like miniImageNet, CIFAR-FS, and CUB. The excellent performance and compelling visualization show that our method can more accurately estimate the ground-truth distributions.
Crowd counting aims to count the number of people in crowded scenes, which is important to the security systems, traffic control and so on. The existing methods typically using local features cannot properly handle the perspective distortion and the varying scales in congested scene images, and henceforth perform wrong people counting. To alleviate this issue, this study proposes a multi‐scale residual feature‐aware network (MSR‐FAN) that combines multi‐scale features using multiple receptive field sizes and learns the feature‐aware information on each image. The MSR‐FAN is trained end‐to‐end to generate high‐quality density map and evaluate the crowd number. The method consists of three parts. To handle the perspective changes problem, the first part, the direction‐based feature‐enhanced network, is designed to encode the perspective information in four directions based on the initial image feature. The second part, the proposed multi‐scale residual block module, gets the global information to handle the represent the regional feature better. This module explores features of different scales as well as reinforce the global feature. The third part, the feature‐aware block, is designed to extract the feature hidden in the different channels. Experiment results based on benchmark datasets show that the proposed approach outperforms the existing state‐of‐the‐art methods.
A novel method to amplify laser pulses in inertial confinement fusion (ICF) facilities is presented, in which twin pulses are employed to propagate along the amplifier in opposite directions. The resulting bidirectional propagation provides a substantially higher extraction efficiency of the amplifier than the conventional multipass architecture for an equal B limit, while keeping the laser fluence at a low level that is beneficial to system reliability and stability. It is shown that an extraction efficiency of ∼61% is achievable under a laser fluence of 10 J cm−2 (1ω, one pulse) in an 18-slab amplifier with the bidirectional amplifying design (slab thickness: 4 cm, small signal gain coefficient: 0.0525 cm−1), while the extraction efficiency is only ∼40% under a fluence of 13 J cm−2 (1ω) for the conventional multipass architecture.