Explore the vast range of titles available.

Human beings solve problems in different granularity worlds and shift from one granularity world to another quickly. It reflects human beings’ intelligence in problem solving to some extent. In the era of big data, some new problems are emerging in real life. For example, traditional big data processing models always compute from raw data, failing to consider the granularity feature of human. Thus, they are hard to solve the 3 V characteristics of big data. Granular computing (GrC) combines the multi-granularity thinking pattern of human intelligence with problem solving mode to deal with big data. Based on the related notions and characteristics of GrC, this paper reviews the previous studies of GrC in three progressive levels: granularity optimization, granularity conversion and multi-granularity joint problem solving. Then we proposed the diagram for relationship among three basic modes of GrC. Furthermore, the feasibility of GrC for big data processing is analyzed. Some research prospects of granular computing are given.

In recent years, stacked a deeper model can get a better super-resolution result, but a large deep model is difficult to train. In this paper, to address the difficulty of training a huge deep image super-resolution model, we propose an efficient progressive training framework with granularity cross for image super-resolution (EPTGC). Splitting the model and combining the use of multiple images with different granularities, not only reduces the difficulty of training the model but also helps the model to learn different granular features, and enhance the ability of the model to recover the image edge information. EPTGC is a plug-and-play approach and can be applied to most image super-resolution models. In the experiments, we apply EPTGC to 8 different models, including the convolutional neural network (CNN) based models and transformer-based models. The results show that using EPTGC improves their ability to recover the edge information of the image and improves their results on the 4 benchmark datasets by a maximum of 0.44 DB on PSNR.

Change detection is an essential and widely utilized task in remote sensing that aims to detect and analyze changes occurring in the same geographical area over time, which has broad applications in urban development, agricultural surveys, and land cover monitoring. Detecting changes in remote sensing images is a complex challenge due to various factors, including variations in image quality, noise, registration errors, illumination changes, complex landscapes, and spatial heterogeneity. In recent years, deep learning has emerged as a powerful tool for feature extraction and addressing these challenges. Its versatility has resulted in its widespread adoption for numerous image-processing tasks. This paper presents a comprehensive survey of significant advancements in change detection for remote sensing images over the past decade. We first introduce some preliminary knowledge for the change detection task, such as problem definition, datasets, evaluation metrics, and transformer basics, as well as provide a detailed taxonomy of existing algorithms from three different perspectives: algorithm granularity, supervision modes, and frameworks in the Methodology section. This survey enables readers to gain systematic knowledge of change detection tasks from various angles. We then summarize the state-of-the-art performance on several dominant change detection datasets, providing insights into the strengths and limitations of existing algorithms. Based on our survey, some future research directions for change detection in remote sensing are well identified. This survey paper sheds some light the topic for the community and will inspire further research efforts in the change detection task.

In order to overcome the limitation of low efficiency of existing granularity reduction algorithms in multi-granulation rough sets, based on matrix method, a fast granularity reduction algorithm is proposed and the time complexity is O(|U|2·|A|+|U|·|A|2). First, the definitions of positive region matrix and granularity column matrix of multi-granulation space are proposed. Second, through the quantity product of these two matrices, the definition of positive region column matrix is presented. Based on the positive region column matrix, cut matrix and matrix norm are defined, respectively. Third, the matrix-based calculation methods of multi-granulation approximation quality and granularity significance are proposed. Finally, a heuristic rule is designed according to the granularity significance, and a matrix-based fast granularity reduction algorithm is proposed. Experimental results demonstrate the effectiveness of the proposed methods.

Fine-grained image recognition is characterized by high interclass object similarities and large intraclass object variations. Many existing works focus on locating more discriminative parts, but it is difficult to extract multigranular features synchronously and fuse them to make joint decisions about various granular parts. To address these issues, this work proposes a novel cross-granularity feature fusion method. First, a multi-granularity feature generator is used to obtain various granularity features simultaneously for mid-level feature maps via its subgenerators. The subgenerators divide the feature maps into blocks to ensure the relative integrity of the local features, and randomly shuffle the divided blocks to increase the variance of the local regions. Then, a cross-granularity feature fusion strategy achieves the joint decision-making of multiple granularity features in fine-grained images. Therefore, the proposed method can extract various granularity features and promote the synergistic interaction of richer granularity features. The effectiveness of the method is verified through comprehensive experiments on three widely-used fine-grained object recognition benchmark datasets and a chip inner structure dataset. The experimental results show that the proposed method significantly outperforms the baseline and exhibits a comparable performance to that of the SOTA method. Source codes are available at https://github.com/ShanWuJ/CGFF

Question answering (QA) technologies are crucial for building conversational AI.  Current research related to QA for the legal domain lacks focus on the organized structure of laws, which are hierarchically segmented into components at varying levels of detail. To address this gap, we propose a new task of granularity-aware legal QA, which accounts for the underlying granularity levels of law components. Our approach encompasses task formulation, dataset creation, and model development. Under the Indonesian jurisdiction, we consider four law component granularity levels: chapters (bab), articles (pasal), sections (ayat), and letters (huruf). We include 15 government regulations (Peraturan Pemerintah) of Indonesia related to labor affairs and build a legal QA dataset with granularity information. We then design a solution for such a task—the first IR system to account for legal component granularity. We implement a customized retriever-reranker pipeline in which the retriever accepts law components of multiple granularities and the reranker is trained for granularity-aware ranking. We leverage BM25 and BERT models as retriever and reranker, respectively, yielding an end-to-end exact match accuracy of 35.68%, which offers a significant improvement (20%) over a strong baseline. The use of reranker also improves the granularity accuracy from 44.86% to 63.24%. In practical context, such a solution can help provide more precise answers, not only from legal chatbots, but also other conversational AI that deals with hierarchically-structured documents.

Most existing results about attribute reduction are reported by considering one and only one granularity, especially for the strategies of searching reducts. Nevertheless, how to derive reduct from multi-granularity has rarely been taken into account. One of the most important advantages of multi-granularity based attribute reduction is that it is useful in investigating the variation of the performances of reducts with respect to different granularities. From this point of view, the concept of Sequential Granularity Attribute Reduction (SGAR) is systemically studied in this paper. Different from previous attribute reductions, the aim of SGAR is to find multiple reducts which are derived from a family of ordered granularities. Assuming that a reduct related to the previous granularity may offer the guidance for computing a reduct related to the current granularity, the idea of the three-way is introduced into the searching of sequential granularity reduct. The three different ways in such process are: (1) the reduct related to the previous granularity is precisely the reduct related to the current granularity; (2) the reduct related to the previous granularity is not the reduct related to the current granularity; (3) the reduct related to the previous granularity is possible to be the reduct related to the current granularity. Therefore, a three-way based forward greedy searching is designed to calculate the sequential granularity reduct. The main advantage of our strategy is that the number of times to evaluate the candidate attributes can be reduced. Experimental results over 12 UCI data sets demonstrate the following: (1) three-way based searching is superior to some state-of-the-art acceleration algorithms in time consumption of deriving reducts; (2) the sequential granularity reducts obtained by proposed three-way based searching will provide well-matched classification performances. This study suggests new trends concerning the problem of attribute selection.

Learning using statistical invariants (LUSI) is a new learning paradigm, which adopts weak convergence mechanism, and can be applied to a wider range of classification problems. However, the computation cost of invariant matrices in LUSI is high for large-scale datasets during training. To settle this issue, this paper introduces a granularity statistical invariant for LUSI, and develops a new learning paradigm called learning using granularity statistical invariants (LUGSI). LUGSI employs both strong and weak convergence mechanisms, taking a perspective of minimizing expected risk. As far as we know, it is the first time to construct granularity statistical invariants. Compared to LUSI, the introduction of this new statistical invariant brings two advantages. Firstly, it enhances the structural information of the data. Secondly, LUGSI transforms a large invariant matrix into a smaller one by maximizing the distance between classes, achieving feasibility for large-scale datasets classification problems and significantly enhancing the training speed of model operations. Experimental results indicate that LUGSI not only exhibits improved generalization capabilities but also demonstrates faster training speed, particularly for large-scale datasets.

The development of functional categories crosslinguistically is an extensively studied and debated topic (i.a., Radford 1990; Boser et al. 1992; Rizzi 1993; Guasti 1993; Clahsen et al. 1994; Friedmann et al. 2021; Heim & Wiltschko 2025). In this paper, I contribute to existing literature by exploring the potential in acquisition of a previously understudied formal notion – categorial granularity (following Biberauer & Roberts 2015; Song 2019; Biberauer 2019). I study the development of the left periphery with a multilingual corpus study on 10 children, across 5 languages. First, a novel contrast is observed: while CP-structures emerge very early, there is virtually no evidence in the production data to assume children are operating with a split, cartographic-type CP until a later stage. Second, I show that acquisition and structural height can mismatch: some structurally very high elements (topics, illocutionary complementisers) emerge very early in several children. I argue that these empirical generalisations pose considerable challenges for any theory of syntactic development assuming (fully) innate categories. This is because contemporary maturational and continuity approaches posit universal categorial sequences of fixed (often cartographic) granularity. Some of them additionally predict a strong correlation between height in a cartographic tree and timing of acquisition (e.g., Friedmann et al. 2021). I interpret these results to stress the analytical strengths of incorporating changes in granularity as part of syntactic development. I develop a neo-emergentist account of the patterns, probing Biberauer & Roberts’s (2015) emergent categorial hierarchy. The data presented provides an initial impetus for a role of granularity in syntactic development and for a reconceptualisation of the latter in terms of emergent categories. I maintain this is a productive way forward, and finish by considering how this neo-emergentist thinking could be extended in future work.

People differ in how specifically they separate affective experiences into different emotion types—a skill called emotion differentiation or emotional granularity. Although increased emotion differentiation has been associated with positive mental health outcomes, little is known about its development. Participants (N = 143) between the ages of 5 and 25 years completed a laboratory measure of negative emotion differentiation in which they rated how much a series of aversive images made them feel angry, disgusted, sad, scared, and upset. Emotion-differentiation scores were computed using intraclass correlations. Emotion differentiation followed a nonlinear developmental trajectory: It fell from childhood to adolescence and rose from adolescence to adulthood. Mediation analyses suggested that an increased tendency to report feeling emotions one at a time explained elevated emotion differentiation in childhood. Importantly, two other mediators (intensity of emotional experiences and scale use) did not explain this developmental trend. Hence, low emotion differentiation in adolescence may arise because adolescents have little experience conceptualizing co-occurring emotions.