Yiying Li

Vision Transformer (ViT) models have recently emerged as powerful and versatile tools for various visual tasks. In this article, we investigate ViT in a more challenging scenario within the context of few-shot conditions. Recent work has achieved promising results in few-shot image classification by utilizing pre-trained vision transformer models. However, this work employs full fine-tuning for the downstream tasks, leading to significant overfitting and storage issues, especially in the remote sensing domain. In order to tackle these issues, we turn to the recently proposed Parameter-Efficient Tuning (PETuning) methods, which update only the newly added parameters while keeping the pre-trained backbone frozen. Inspired by these methods, we propose the Meta Visual Prompt Tuning (MVP) method. Specifically, we integrate the prompt-tuning-based PETuning method into the meta-learning framework and tailor it for remote sensing datasets, resulting in an efficient framework for Few-Shot Remote Sensing Scene Classification (FS-RSSC). Moreover, we introduce a novel data augmentation scheme that exploits patch embedding recombination to enhance the data diversity and quantity. This scheme is generalizable to any network that employs the ViT architecture as its backbone. Experimental results on the FS-RSSC benchmark demonstrate the superior performance of the proposed MVP over existing methods in various settings, including various-way-various-shot, various-way-one-shot, and cross-domain adaptation.

The sparsity of extrinsic rewards presents a significant challenge for deep reinforcement learning (DRL). As an alternative, researchers have focused on intrinsic rewards to improve exploration efficiency. One of the most representative approaches is utilizing curiosity. However, the challenge of designing effective intrinsic rewards remains, as artificial curiosity differs significantly from human curiosity. In this article, we introduce a novel curiosity approach for DRL, named DyMeCu, which stands for Dynamic Memory-based Curiosity. Inspired by human curiosity and information theory, DyMeCu constructs a dynamic memory using the online learner following the bootstrap paradigm. Additionally, we design a two-learner architecture inspired by ensemble techniques to access curiosity better. The information gap between the two learners serves as the intrinsic reward for agents, and the state information is consistently consolidated into the dynamic memory. Compared with previous curiosity methods, DyMeCu can better mimic human curiosity by using a dynamic memory that can be dynamically grown based on a bootstrap paradigm with two learners. Large-scale empirical experiments on multiple benchmarks, including DeepMind Control Suite and Atari Suite, demonstrate that DyMeCu outperforms competitive curiosity-based methods with or without extrinsic rewards. In the Atari Suite, DyMeCu achieves a mean human-normalized score of 5.076 on a subset of 26 Atari games, achieving a 77.4% relative improvement over the best other baselines. In the DeepMind Control Suite, DyMeCu presents new state-of-the-art results across 11 tasks of all 12 when compared to curiosity-based methods and other pre-training strategies.

Reinforcement learning (RL) has achieved promising results in solving numerous challenging sequential decision problems. To address the issue of sparse extrinsic rewards, researchers have proposed intrinsic rewards, enabling the agent to acquire skills that may prove valuable in the pursuit of future rewards. One representative approach for generating intrinsic rewards involves constructing a predictive model to assess the novelty of states. However, due to the stochastic nature of complex environments, intrinsic rewards can be noisy. Directly employing noisy forward predictions to supervise policies can be detrimental to learning performance and efficiency. Many recent studies utilize the $\ell _{2}$ norm or variance to measure novelty, which further amplifies the noise through squaring operations. In this paper, we aim to tackle these challenges by leveraging Nuclear Norm Maximization (NNM). Specifically, we propose a novel curiosity reward that accurately quantifies the novelty of the exploration environment while exhibiting a high tolerance for noise and outliers. Our extensive experiments in various benchmark environments demonstrate that NNM achieves state-of-the-art performance compared to previous curiosity-based methods. When trained solely with intrinsic rewards, NNM achieves a human-normalized score of 1.09 on a subset of 26 Atari games, twice the performance of methods based on competitive intrinsic rewards.

Power transformers are one of the main equipment in power production, with high cost and long manufacturing time. If a fault occurs during the power supply process, it will prevent the normal operation of the power system and result in no electricity available to power users. One of the main factors affecting the safe operation of transformers is short circuit fault, and short circuit faults at the outlet of substations or in close proximity can also pose a serious threat to transformers. This article simulates transformer short-circuit faults and establishes a simulation model using MATLAB/simulink to verify the harm caused by transformer short-circuit. Verification has shown that short circuit faults pose significant risks.

In China, aging is becoming an increasingly serious issue, and the Chinese government are paying more attention to the life satisfaction of the elderly. Nevertheless, in their daily lives, the elderly are often discriminated against, which may have a negative impact on their life satisfaction. To enable a better understanding of these relationships, we discuss the factors affecting the macro-system (national identity) and micro-system (sense of community) of the elderly. Three hundred and ninety-one elderly people (60–101 years old; 121 males, 270 females) from three communities in the Anhui and Shandong provinces of China participated in our study. Each participant completed the appropriate questionnaires, including: perceived discrimination measure, national identity questionnaire, sense of community questionnaire, and life satisfaction questionnaire. The results of structural equation modeling revealed that perceived discrimination negatively influenced life satisfaction through national identity and community. Perceived discrimination was found to negatively predict national identity, suggesting that perceived discrimination brings a negative influence to national identity within Chinese culture. The relationship between perceived discrimination and life satisfaction was partially mediated by the chain of national identity and sense of community. The size of the total mediation effect was 32.17%. The relationship between perceived discrimination and life satisfaction, when mediated by national identity or sense of community, was not significant. This suggests that the application of the rejection-identification model to the elderly in China may produce different results. The limitations and the implications of our study were considered in discussion.