No abstract

Convolutional neural network (CNN) based methods have dominated the field of aerial scene classification for the past few years. While achieving remarkable success, CNN-based methods suffer from excessive parameters and notoriously rely on large amounts of training data. In this work, we introduce few-shot learning to the aerial scene classification problem. Few-shot learning aims to learn a model on base-set that can quickly adapt to unseen categories in novel-set, using only a few labeled samples. To this end, we proposed a meta-learning method for few-shot classification of aerial scene images. First, we train a feature extractor on all base categories to learn a representation of inputs. Then in the meta-training stage, the classifier is optimized in the metric space by cosine distance with a learnable scale parameter. At last, in the meta-testing stage, the query sample in the unseen category is predicted by the adapted classifier given a few support samples. We conduct extensive experiments on two challenging datasets: NWPU-RESISC45 and RSD46-WHU. The experimental results show that our method yields state-of-the-art performance. Furthermore, several ablation experiments are conducted to investigate the effects of dataset scale, the impact of different metrics and the number of support shots; the experiment results confirm that our model is specifically effective in few-shot settings.

No abstract

Main-chain cholesteric liquid crystal polymers are a promising candidate for the development of responsive photonic devices due to the combination of selective reflection and soft, elastic properties, but it is difficult to enhance these materials with new kinds of responsiveness due to the inherent lack of mesogenic side groups. Here, a new strategy is showed to obtain a dualresponsive elastic cholesteric polymer material by preparing a semi-interpenetrating network consisting of a cholesteric main-chain polymer and a hygroscopic poly(ampholyte). The material is shown to undergo a redshift of the reflected color upon swelling with water, while the color blueshifts when a strain is applied. Color patterns can be prepared by localized photopolymerization at different temperatures, leading to brightly colored responsive images with high contrast. Due to the elastic nature of the material, it can easily be made into a wearable device, and its application as a multifunctional smart sensor for sweat detection and movement detection is demonstrated. The results show that new responsiveness can be added to main-chain cholesteric polymers by preparation of interpenetrating networks, which can be further extended to develop various kinds of multi-responsive smart materials.

HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.