Search

The low-loss interconnection of multicore fiber with other fibers or photonic integrated circuits poses significant challenges in photonic packaging. Femtosecond laser processing has been harnessed here to combine three-dimensional writing of low-loss optical waveguides with laser-guided etching of self-aligning fiber sockets. The silica platform facilitated efficient packaging of multicore and single-core fibers into the underlying photonic circuitry, providing submicron registration of the waveguide cores. The direct writing approach offers facile connectivity of specialty fiber types with high-bandwidth optical links, high channel-density integrated chips, and micro-scale sensors.

Self-supervised learning, which leverages unlabeled data to learn useful feature representations by constructing auxiliary tasks, has been widely explored in few-shot scene classification to improve the feature representation and generalization capabilities of deep models in scarce data. However, most of the current related work adopts specific self-supervised auxiliary tasks (SSATs) for combinatorial improvement, and does not explore the intrinsic connection between different pretext tasks. In practice, the linkage of SSATs is complex, and the optimization of task-sharing parameters by minimizing linear combinations of losses can be conflicting. In addition, although a single combination of SSAT can improve certain performance on the baseline, it is not the personalized optimal solution on various remote sensing datasets with diverse properties. In this article, we propose a collaborative self-supervised evolution (so-called CSENet) framework for few-shot remote sensing scene classification to automatically search for appropriate weights in balancing the task conflicts. In contrast to most existing methods, which consider all SSATs to be equally efficacious or fixed-weighted for the few-shot main task, CSENet achieves autonomous co-evolutionary optimization by encoding arbitrary self-supervised weights. Specifically, the complex self-supervised combinations for different remote sensing data are transformed into an evolutionary optimization problem, where chromosomes with weighting variables obtain the optimal combination with genetic operators. Based on the transfer learning few-shot training paradigm, CSENet first efficiently searches for optimal self-supervised combinations with potential by the proposed automatic collaborative evolution strategy and automatically adjusts the weights without manual settings. Importantly, CSENet provides both inductive and transductive inference, and supports the embedding of arbitrary SSATs. The effectiveness of the proposed framework is demonstrated by state-of-the-art (SOTA) results on three benchmark datasets.

Pruning techniques have been utilized widely for convolutional neural networks (CNNs) to reduce the computation resources in remote sensing scene image classification. However, conventional pruning techniques are weight-based, which cannot balance the pruning ratio and representation ability appropriately. In this article, we propose a data customization-based multiobjective optimization pruning (DCMOP) framework for the pruning in remote sensing scene image classification, which can not only tradeoff between pruning ratio and capability for CNNs but also speed up the evolutionary process for the pruning. We adopt the multiobjective evolutionary algorithms (MOEAs) to search for a tradeoff between the pruning ratio and capability for CNNs. However, a big concern of pruning for networks via MOEAs is that the evaluation of subnetworks is time-consuming. This originates that the slimmed subnetworks require a lot of retraining operation, which will burden the hardware. In order to alleviate this limitation, we design a data customization-based proxy mechanism (DCPM) to reduce the size of the input dataset in terms of the structure of the slimmed subnetwork to accelerate significantly the evolutionary process for the pruning. According to this, our proposed DCMOP achieves the pruning with higher efficiency and performance by cooperating with MOEAs and DCPM. Experimental results based on four datasets of AID, NWPURESISC45, PatternNet, and WHU-RS19 show that the proposed DCMOP can achieve a balance between model performance and pruning rate, while obviously reducing the time cost of the pruning.

The existing few-shot scene classification (FSSC) algorithms have achieved satisfactory results, but they are limited by the paradigm of centralized machine learning, i.e., private remote sensing data need to be centralized on a certain server for training. However, remote sensing images generally contain sensitive information such as national security and company privacy, so it is realistically difficult to collect remote sensing data from all the parties. Therefore, there is a pressing requirement in FSSC for a novel paradigm to achieve multiparty collaborative learning without compromising remote sensing data privacy. In this article, we formulate a novel personalized multiparty few-shot learning (PMPFSL) paradigm for remote sensing scene classification. In PMPFSL, different participants can achieve multiparty collaborative learning without sacrificing the privacy of their local data, and their respective local models are able to recognize the unseen remote sensing scene categories with a small number of labeled samples. Importantly, the proposed PMPFSL is applicable to various multiparty learning (MPL) algorithms and FSSC networks. Moreover, to address the problems of local model overfitting and poor discriminability of few-shot metrics, we propose the personalized adaptive distillation (PAD) scheme and multiscale feature matching network (MSFMNet) on PMPFSL, respectively. Specifically, each participant obtains the MSFMNet with initialization parameters, and implements a certain number of local training on their respective private machines. Global aggregation is subsequently achieved by uploading only the local models to the central server. In a new round of local training, the participants realize personalized data adaptation to the global model based on the PAD. Overall, the proposed PMPFSL customizes a personalized few-shot model for each participant that is more tailored to their respective remote sensing scenarios. The experimental results demonstrate that our PMPFSL is superior in three benchmark FSSC datasets. We also extensively studied and analyzed the contributions of PAD and MSFMNet in the proposed PMPFSL framework.

The powerful deep learning models in remote sensing are inseparable from the support of massive data. However, the privacy and sensitivity of remote sensing data (RSD) restrict the possibility of each party to collaboratively train and share a large general model. Although multiparty learning (MPL) is a feasible solution, it is difficult for the existing MPL methods to uniformly process different remote sensing tasks (RSTs), and the data held by each party is nonindependent and identically distributed (non-IID), heterogeneous, and multisources. Therefore, it is urgent to explore a solution for the personalized processing of different RSTs. In this article, we formulate a novel multiparty personalized collaborative learning (MPCL) framework in terms of models and tasks. Specifically, in each iteration of the communication round, we aim to decouple personalized model optimization from global model learning. Different participants are allowed to explore their personalized local models at a certain distance from the global aggregation models according to the characteristics of their local data. In terms of task personalization, MPCL provides different personalized global models to handle the corresponding RSTs. For participants with different RSTs, it can be implemented in the multitask collaborative training strategy to explore the connection between different tasks. To demonstrate the feasibility of MPCL, we take remote sensing image (RSI) classification as a case study and provide a detailed feasibility scheme. We constructed four benchmark datasets compliant with MPL and personalized MPL, including single-source and multisource about SAR, hyperspectral, and optical RSD. The experimental results demonstrate that our MPCL is superior in these four RSDs, which ranked first in the competition with the classic or state-of-the-art (SOTA) MPL and personalized MPL algorithms. In addition, the scalability of MPCL is also verified on image segmentation RSTs of building and road extraction.

End-to-end deep clustering method utilizes deep neural networks to jointly learn representation features and clustering assignments. Although many k-means-friendly deep clustering models have been explored, the existing division-based methods tend to directly implement clustering with a specific number of clusters, which suffers from poor performance resulted from indistinguishable clusters, and contributes to bad local optimum. At the same time, the representation learning of fuzzy $c$-means clustering in the feature space still needs more research. In this article, a deep fuzzy curriculum clustering method with the learning strategy of clustering from easy to complex automatically is proposed to tackle the above issues. First, considering the soft flexible allocation of fuzzy $c$-means and the preservation of local structure of original data, the fuzzy clustering loss and the autoencoder's reconstruction loss are constructed to learn the embedded features and clustering centers simultaneously. Second, curriculum loss is introduced into the constraint to make clusters successively merge in line with implementing clustering from easy to complex, and realize the bottom-up deep aggregative clustering automatically. In addition, novel curriculum information is proposed as constraint to guide the merging of clusters belonging to the same class. Experimental results on four real-world datasets show the superiority of the proposal.