Global contextual information is crucial for the semantic segmentation of remote sensing (RS) images. However, the majority of current approaches depend on convolutional neural networks (CNNs). Due to the local receptive fields inherent in convolutional operations, these networks typically capture image features within limited areas and struggle to comprehend broader contextual information in the images. In this study, a dual-branch encoding approach, DESformer, is proposed, integrating transformers with CNN, to effectively capture global multiscale context information and enhance edge feature extraction. In addition, DESformer incorporates a feature interaction module (FIM) to combine local features with global representations extracted by transformers and CNN, respectively, across different resolutions. This approach enhances the capability to capture local features in RS images and improves the understanding of extensive spatial relationships. Subsequently, we employ a novel top-down approach for global supervision of the traditional feature pyramid multilevel visual integration (MVI) module, by harnessing the clear visual center information obtained from the deepest internal features. To successfully concentrate on important information and preserve sensitivity to features at various scales, the preceding shallow features are muted. In addition, FIAB-Loss, a loss function is introduced, combining a focal loss with IOU and active boundary loss (ABL). This composite loss function strengthens the model’s focus on challenging-to-distinguish categories. Extensive experiments conducted on three datasets, including the semantic segmentation of lakes in the Tibetan Plateau and the ISPRS’s Vaihingen benchmark, validate the efficacy of the proposed method. The experimental results indicate that the network exhibits exceptional performance in processing VHR images and accurately extracting edge features.

Graph Neural Networks (GNNs) are used for graph data processing across various domains. Centralized training of GNNs often faces challenges due to privacy and regulatory issues, making federated learning (FL) a preferred solution in a distributed paradigm. However, GNNs may inherit biases from training data, causing these biases to propagate to the global model in distributed scenarios. To address this issue, we introduce $\mathrm{F}^{2}$GNN, a Fair Federated Graph Neural Network, to enhance group fairness. Recognizing that bias originates from both data and algorithms, $\mathrm{F}^{2}$GNN aims to mitigate both types of bias under federated settings. We offer theoretical insights into the relationship between data bias and statistical fairness metrics in GNNs. Building on our theoretical analysis, $\mathrm{F}^{2}$GNN features a fairness-aware local model update scheme and a fairness-weighted global model update scheme, considering both data bias and local model fairness during aggregation. Empirical evaluations show $\mathrm{F}^{2}$GNN outperforms SOTA baselines in fairness and accuracy.

The participatory nature of federated learning (FL) makes it attractive for fingerprinting-based indoor localization in multibuilding and multifloor environments. A group of sensing clients can collaboratively leverage their private, local fingerprint data to help their edge server update a location prediction model. However, it is challenging to jointly handle the two involved issues, i.e., building-floor classification (BFC) and latitude–longitude regression (LLR), in a wide 3-D space through enabling FL on decentralized yet heterogeneous data and over an imperfect wireless network. In this article, we confront these challenges and propose an FL framework, FedLoc3D, for both BFC and LLR. Specifically, the former issue is addressed by an FedDSC-BFC approach, which generates a multilabel classification model based on a convolutional neural network with depthwise separable convolutions. The latter issue is addressed by an FedADA-LLR approach, which develops a multitarget regression model based on a deep neural network with autoencoder and data augmentation. Extensive experiments on a real-world data set of WiFi fingerprints are carried out, and our approaches with enhanced capabilities of feature extraction, generalization, and convergence are validated to improve both localization accuracy and learning efficiency under data heterogeneity and network instability.

Active learning has become a prevalent technique for designing label-efficient algorithms, where the central principle is to only query and fit “informative” labeled instances. It is, however, known that an active learning algorithm may incur unfairness due to such instance selection procedure. In this paper, we henceforth study metric-fair active learning of homogeneous halfspaces, and show that under the distribution-dependent PAC learning model, fairness and label efficiency can be achieved simultaneously. We further propose two extensions of our main results: 1) we show that it is possible to make the algorithm robust to the adversarial noise – one of the most challenging noise models in learning theory; and 2) it is possible to significantly improve the label complexity when the underlying halfspace is sparse.

Learning program representations has been the core prerequisite of code intelligence tasks (e.g., code search and code clone detection). The state-of-the-art pre-trained models such as CodeBERT require the availability of large-scale code corpora. However, gathering training samples can be costly and infeasible for domain-specific languages such as Solidity for smart contracts. In this paper, we propose Zecoler, a zero-shot learning approach for code representations. Zecoler is built upon a pre-trained programming language model. In order to elicit knowledge from the pre-trained models efficiently, Zecoler casts the downstream tasks to the same form of pre-training tasks by inserting trainable prompts into the original input. Then, it employs the prompt learning technique to optimize the pre-trained model by merely adjusting the original input. This enables the representation model to efficiently fit the scarce task-specific data while reusing pre-trained knowledge. We evaluate Zecoler in three code intelligence tasks in two programming languages that have no training samples, namely, Solidity and Go, with model trained in corpora of common languages such as Java. Experimental results show that our approach significantly outperforms baseline models in both zero-shot and few-shot settings.

The worker-task matching problem brings up unique characteristics that are not present in traditional matching scenarios, i.e., the huge flow of tasks with short lifespans, the importance of workers’ capabilities, and the quality of the completed tasks. These characteristics further pose significant challenges of data sparsity and comprehensive modeling.To address the two challenges, this paper proposes MvkGAN, a multi-view attention network on a bi-collaborative knowledge graph (BicKG). The core ideas of our work are 1) building BicKG from the data of workers, tasks, their interactions, and domain knowledge, and then leveraging it to reveal the latent interactions between workers and tasks to mitigate the data sparsity challenge; and 2) designing a multi-view knowledge graph attention network (MvkGAN) which learns to match workers and tasks, to meet the comprehensive modeling challenge. In this network, different features are organized as multiple views and these views are further connected by the attention mechanism.We have implemented MvkGAN and evaluated it against five state-of-the-art approaches (Wide&Deep, DeepFM, KGAT, Crow-dRex and PJFNN) on two real-world datasets. The evaluation results show that MvkGAN improves the accuracy by 6.90% and F1-score by 5.52% on average, and also has the ability of generating reasonable explanations.

The emergence of Hive greatly facilitates the management of massive data stored in various places. Meanwhile, data scientists face challenges during HiveQL programming - they may not use correct and/or efficient HiveQL statements in their programs; developers may also introduce anti-patterns indeliberately into HiveQL programs, leading to poor performance, low maintainability, and/or program crashes. This paper presents an empirical study on HiveQL programming, in which 38 HiveQL anti-patterns are revealed. We then design and implement DeFiHap, the first tool for automatically detecting and fixing HiveQL anti-patterns. DeFiHap detects HiveQL anti-patterns via analyzing the abstract syntax trees of HiveQL statements and Hive configurations, and generates fix suggestions by rule-based rewriting and performance tuning techniques. The experimental results show that DeFiHap is effective. In particular, DeFiHap detects 25 anti-patterns and generates fix suggestions for 17 of them.

Despite tremendous developments in preoperative imaging that have enabled physicians to identify cancers with remarkable precision, limited options for intraoperative imaging have left many surgeons ill-equipped to locate tumors in the operating room. Near-infrared fluorescence image-guided surgery has offered to use near-infrared fluorescent dyes and near-infrared sensitive cameras to highlight diseased tissue, but state-of-the-art imaging systems have been unable to provide both the single sensor architecture and the high dynamic range required to facilitate precise surgical procedures under operating room illumination. In seeking a solution, we have monolithically integrated an array of forward-biased photodiodes and an array of interference filters to provide a logarithmic photoresponse across four spectral channels. The resulting single-chip snapshot multispectral imaging system provides an instantaneous dynamic range of >120 dB and a maximum signal-to-noise ratio of ∼56 dB across three color channels and one near-infrared channel. Capable of detecting less than 50 nM of the clinically-relevant fluorescent dye indocyanine green, this image sensor offers the high performance required for real-world surgical application.

Near-infrared fluorescence image-guided surgery relies on an interdisciplinary community to develop near-infrared fluorescent markers and near-infrared sensitive cameras capable of mapping relevant structures during surgical procedures. As biochemists pursue a new generation of near-infrared fluorophores aimed at surgical oncology and other applications, optoelectronic engineers developing near-infrared imagers have been slow to adopt architectural improvements that will enhance outcomes in existing operations and to document optoelectronic characteristics that are needed to predict endpoints for new procedures. Here we present a single-chip snapshot multispectral imaging system that integrates arrays of bandpass optical filters and six-transistor backside-illuminated pixels to provide RGB-NIR images with low read noise (3.47 e−) and high dynamic range (81 dB). This imaging system is being used in clinical studies for sentinel lymph node mapping during breast cancer surgery.

A 110 × 64 pixel CMOS image sensor integrated with pixelated spectral interference filters is used for image guided surgery. The sensor operates with short exposure times for capturing visible light using blue, green, and red pixelated interference filters, and long exposure time for capturing near-infrared fluorescence with a co-located, pixelated NIR filter. The sensor was used to successfully detect the fluorescence of ICG accumulation in sentinel lymph node on patients with breast cancer.

CMOS Polarization image sensors can detect the polarization of an incident light, from which a lot of information can be derived about the properties and shape of the images objects. This paper proposes a current mode polarization analyzer, based on a three-parameter polarization analysis methodology. The procedure of the calculation of the intensity, polarization degree, and the polarization angle is optimized in a format for hardware friendly implementation. The proposed analysis procedure is implemented using only absolute adder/subtractors and multiplier/dividers. In this work, the multiplier/divider is performed in two modes: i) geometric mean calculation mode, and ii) square/divider mode. Both a parallel implementation, which employs five multiplier/divider, for the optimization of processing efficiency, and a serial implementation, which employs two multiplier/divider, for the optimization of power efficiency, are designed and compared. A prototype chip of the proposed design was implemented in 0.5μm 3M2P standard CMOS technology, occupying a silicon area of 150 × 140 μm2.

In this paper, a bioinspired monolithic complementary metal-oxide-semiconductor (CMOS) polarization image sensor is described as a solution to real-time polarization image capture. Metallic wire-grid gratings are integrated onto standard CMOS image sensor arrays with different orientations. A numerical analysis is performed to guide the design of the wire-grid arrays. Experimental results from different CMOS processing units are compared. A current-mode polarization processing unit is designed, fabricated, and tested in order to perform the extraction of the polarization characteristics from the captured intensities. This paper illustrates how polarization image processing can be used to monitor live cells. Several polarization processing methods with different computational complexity and data requirements have been applied and compared.