Dense pixel-wise labeling of large-scale remote sensing images (RSI) is very time-consuming, while sparse labels (i.e., points, scribbles, or blocks) can be an efficient way to reduce labeling costs. Most existing sparse label-based methods adopt only one type of label for image segmentation, which cannot reflect the complex land covers in the RSI for training the model, thus leading to inferior segmentation performance. We observe that land covers with different shapes and complexity can be optimally represented by different sparse labels. Inspired by this observation, we propose a novel sparse labeling framework, termed Hybrid Sparse Labeling (HSLabeling), for large-scale RSI segmentation. Our HSLabeling can adaptively select the optimal hybrid sparse labels for different land covers, according to labeling cost and segmentation contribution of different sparse labels. Specifically, we first propose a label segmentation contribution information estimation module that estimates the information of different sparse labels according to the diversity and shape of land covers. After that, we propose an Optimal Hybrid Labeling Strategy (OHLS) to assign optimal types of labels for different land covers. In the OHLS, label assignment is formulated as an optimization problem that trades off label segmentation contribution information and labeling cost. We employ the greedy algorithm to efficiently solve the optimization problem and adaptively assign labels for varied land covers. Extensive experiments on three large-scale RSI datasets have demonstrated that our HSLabeling achieves almost fully supervised performance with extremely low labeling costs. In addition, compared with the single type sparse label, HSLabeling can also utilize much lower labeling costs to obtain the same performance. The source code is available at https://github.com/linjiaxing99/HSLabeling.

In long-term Earth observation, change detection (CD) is a crucial and intricate task with applications spanning diverse fields, including land resource planning and natural disaster monitoring. Most existing CD approaches typically output segmentation results in raster format. However, raster format results suffer from higher memory usage, poorer shape accuracy, magnified distortions, and challenges in topological editing. To address the issues of raster format, we propose a novel end-to-end change vectorization network (CVNet), which is the first attempt to extract changes using vector format. The CVNet directly learns the vector components of changed objects and uses them to construct vectors. Specifically, since the vectorization of CD faces the inherent imbalance between changed and unchanged samples, we first introduce the Change-Collector to collect the changed regions and combine them into more compact samples. Next, the vector components learning model (VCLM) is introduced to capture the fundamental components for constructing the vectors, including change maps, junction positions, and segmentation masks. Finally, the changed instances obtained from the masks are used to divide and connect junctions to generate the vector output. To verify the effectiveness of the proposed framework, we construct two building change vectorization datasets by modifying the WHU-CD and LEVIR-CD benchmarks. Experimental results demonstrate that the CVNet outperforms the existing postprocess vectorization methods in terms of the visual effect and all evaluation metrics. The dataset and source code will be made publicly available athttps://github.com/yyyyll0ss/CVNet.

Information Extraction mainly consists of three sub-tasks, Named Entity Recognition, Relation Extraction and Event Extraction. Although these sub-tasks are highly correlated with each other, most previous works simply focus on part of them and ignore the interactions among different sub-tasks. Recently, some graph-based models are proposed to cover all the interactions among different IE sub-tasks. However, the use of Graph Neural Network brings heavy computation burden, damaging the model efficiency. In this paper, we propose a double-table framework, TableIE, to capture the interactions among IE sub-tasks as well as improve the model efficiency. Specifically, TableIE has an entity-relation table and an event table, based on which we propose both within-table and cross-table interaction through a novel table integration technique. Such technique makes use of an information-aware mask to extract more essential information in the table during the integration, which we call discriminative interaction. Our extensive experiments demonstrate that TableIE outperforms the previous state-of-the-art up to 1.4 on the ACE05 dataset. Besides, since TableIE does not involve the time-consuming graph operation, it is also more efficient than the previous graph-based models, with 13x speed-up in the inference stage. Our code is available at https://github.com/PKUnlp-icler/TableIE

Unlabeled Entity Problem (UEP) in Named Entity Recognition (NER) datasets seriously hinders the improvement of NER performance. This paper proposes SCL-RAI to cope with this problem. Firstly, we decrease the distance of span representations with the same label while increasing it for different ones via span-based contrastive learning, which relieves the ambiguity among entities and improves the robustness of the model over unlabeled entities. Then we propose retrieval augmented inference to mitigate the decision boundary shifting problem. Our method significantly outperforms the previous SOTA method by 4.21% and 8.64% F1-score on two real-world datasets.

BACKGROUND: Time- and dose-to-event phenotypes used in basic science and translational studies are commonly measured imprecisely or incompletely due to limitations of the experimental design or data collection schema. For example, drug-induced toxicities are not reported by the actual time or dose triggering the event, but rather are inferred from the cycle or dose to which the event is attributed. This exemplifies a prevalent type of imprecise measurement called grouped failure time, where times or doses are restricted to discrete increments. Failure to appropriately account for the grouped nature of the data, when present, may lead to biased analyses. RESULTS: We present groupedSurv, an R package which implements a statistically rigorous and computationally efficient approach for conducting genome-wide analyses based on grouped failure time phenotypes. Our approach accommodates adjustments for baseline covariates, and analysis at the variant or gene level. We illustrate the statistical properties of the approach and computational performance of the package by simulation. We present the results of a reanalysis of a published genome-wide study to identify common germline variants associated with the risk of taxane-induced peripheral neuropathy in breast cancer patients. CONCLUSIONS: groupedSurv enables fast and rigorous genome-wide analysis on the basis of grouped failure time phenotypes at the variant, gene or pathway level. The package is freely available under a public license through the Comprehensive R Archive Network.

Parametric feature selection methods for machine learning and association studies based on genetic data are not robust with respect to outliers or influential observations. While rank-based, distribution-free statistics offer a robust alternative to parametric methods, their practical utility can be limited, as they demand significant computational resources when analyzing high-dimensional data. For genetic studies that seek to identify variants, the hypothesis is constrained, since it is typically assumed that the effect of the genotype on the phenotype is monotone (e.g., an additive genetic effect). Similarly, predictors for machine learning applications may have natural ordering constraints. Cross-validation for feature selection in these high-dimensional contexts necessitates highly efficient computational algorithms for the robust evaluation of many features. We have developed an R extension package, fastJT, for conducting genome-wide association studies and feature selection for machine learning using the Jonckheere-Terpstra statistic for constrained hypotheses. The kernel of the package features an efficient algorithm for calculating the statistics, replacing the pairwise comparison and counting processes with a data sorting and searching procedure, reducing computational complexity from O( n 2 ) to O( n log( n )). The computational efficiency is demonstrated through extensive benchmarking, and example applications to real data are presented. fastJT is an open-source R extension package, applying the Jonckheere-Terpstra statistic for robust feature selection for machine learning and association studies. The package implements an efficient algorithm which leverages internal information among the samples to avoid unnecessary computations, and incorporates shared-memory parallel programming to further boost performance on multi-core machines.

Summary: CRISPR-Cas9 and shRNA high-throughput sequencing screens have abundant applications for basic and translational research. Methods and tools for the analysis of these screens must properly account for sequencing error, resolve ambiguous mappings among similar sequences in the barcode library in a statistically principled manner, and be computationally efficient. Herein we present bcSeq, an open source R package that implements a fast and parallelized algorithm for mapping high-throughput sequencing reads to a barcode library while tolerating sequencing error. The algorithm uses a Trie data structure for speed and resolves ambiguous mappings by using a statistical sequencing error model based on Phred scores for each read. Availability and implementation: The package source code and an accompanying tutorial are available at http://bioconductor.org/packages/bcSeq/. Supplementary information: Supplementary data are available at Bioinformatics online.