Task Knowledge Research Articles

UDA-GS: A cross-center multimodal unsupervised domain adaptation framework for Glioma segmentation

Gliomas are the most common and malignant form of primary brain tumors. Accurate segmentation and measurement from MRI are crucial for diagnosis and treatment. Due to the infiltrative growth pattern of gliomas, their labeling is very difficult. In turn, the already available annotated datasets, such as well-known BraTS, are difficult to generalize to multicenter unannotated datasets due to the variations in imaging machines and parameters. To address this challenge, a novel unsupervised domain adaptation framework for glioma segmentation (UDA-GS) is proposed. UDA-GS uses GliomaMix to mix labeled tumors with unlabeled images and aligns the features of the same tumor, allowing the network to adapt to different backgrounds across different centers. Additionally, the framework leverages tumor information generated by GliomaMix as prior knowledge for self-supervised regression tasks to enhance feature encoding for tumors in different domains. Using Mean-Teacher as the basic framework, UDA-GS also incorporates weighted consistency regularization and mask combining strategy to achieve efficient unsupervised domain adaptation. Quantitative and qualitative evaluations were conducted on 1179 cases across 27 centers, without requiring any local annotations. The results demonstrate that UDA-GS outperforms the second-best method in terms of Dice coefficient segmentation metrics by 18.2 %, 6.9 %, and 4.6 % for the whole tumor, tumor core, and enhanced tumor, respectively, on the internal testing set. Additionally, the evaluations reveal that doctors express greater satisfaction with the segmentation outcomes achieved by UDA-GS in comparison to other methods including the segment anything model (SAM).

Using Natural Language to Improve Hierarchical Reinforcement Learning in Games

This work investigates how natural language task descriptions can accelerate reinforcement learning in games. Recognizing that human descriptions often imply a hierarchical task structure, we propose a method to extract this hierarchy and convert it into "options" – policies for solving subtasks. These options are generated by grounding natural language descriptions into environment states, which are then used as task boundaries to learn option policies either by leveraging prior successful traces or from human created walkthroughs. We evaluate our approach in both a simpler grid-world environment and the more complex text-based game Zork, comparing option-based agents against standard Q-learning and random agents. Our results demonstrate the effectiveness of incorporating natural language task knowledge for faster and more efficient reinforcement learning across different environments and Q-learning algorithms, including tabular Q-learning and Deep Q-Networks.

Confidence regulates feedback processing during human probabilistic learning.

Uncertainty presents a key challenge when learning how best to act to attain a desired outcome. People can report uncertainty in the form of confidence judgments, but how such judgments contribute to learning and subsequent decisions remains unclear. In a series of three experiments employing an operant learning task, we tested the hypothesis that confidence plays a central role in learning by regulating resource allocation to the seeking and processing of feedback. We predicted that, as participants' confidence in their task knowledge grew, they would discount feedback when it was provided and be correspondingly less willing to pay for it when it was costly. Consistent with these predictions, we found that higher confidence was associated with reduced electrophysiological markers of feedback processing and decreased updating of beliefs following feedback receipt. Bayesian modeling suggests that this decrease in processing was due to a drop in the expected informative value of novel information when participants were highly confident. Thus, when choosing whether to pay a fee to receive further feedback, participants' subjective confidence, rather than the objective accuracy of their decisions, guided their choices. Overall, our results suggest that confidence regulates learning and subsequent decision making. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Audio-visual event localization with dual temporal-aware scene understanding and image-text knowledge bridging

Audio-visual event localization (AVEL) task aims to judge and classify an audible and visible event. Existing methods devote to this goal by transferring pre-trained knowledge as well as understanding temporal dependencies and cross-modal correlations of the audio-visual scene. However, most works comprehend the audio-visual scene from an entangled temporal-aware perspective, ignoring the learning of temporal dependency and cross-modal correlation in both forward and backward temporal-aware views. Recently, transferring the pre-trained knowledge from Contrastive Language-Image Pre-training model (CLIP) has shown remarkable results across various tasks. Nevertheless, since audio-visual knowledge of the AVEL task and image-text alignment knowledge of the CLIP exist heterogeneous gap, how to transfer the image-text alignment knowledge of CLIP into AVEL field has barely been investigated. To address these challenges, a novel Dual Temporal-aware scene understanding and image-text Knowledge Bridging (DTKB) model is proposed in this paper. DTKB consists of forward and backward temporal-aware scene understanding streams, in which temporal dependencies and cross-modal correlations are explicitly captured from dual temporal-aware perspectives. Consequently, DTKB can achieve fine-grained scene understanding for event localization. Additionally, a knowledge bridging (KB) module is proposed to simultaneously transfer the image-text representation and alignment knowledge of CLIP to AVEL task. This module regulates the ratio between audio-visual fusion features and CLIP’s visual features, thereby bridging the image-text alignment knowledge of CLIP and the audio-visual new knowledge for event category prediction. Besides, the KB module is compatible with previous models. Extensive experimental results demonstrate that DTKB significantly outperforms the state-of-the-arts models.

SPIRF-CTA: Selection of parameter importance levels for reasonable forgetting in continuous task adaptation

Humans can adapt to changing environments and tasks and consolidate their previous knowledge by constantly learning and practicing new knowledge; however, it is extremely challenging for artificial intelligence to achieve this goal. With the development of the field of artificial intelligence, research on overcoming catastrophic forgetting in continuous learning is also faced with the challenges of focusing on the most important parameters of the current task, retaining knowledge from previous tasks and adapting it to new ones, and making better use of knowledge from previous and new tasks. To solve these problems, this article proposes a reasonable forgetting method, which is called selection of parameter importance levels for reasonable forgetting in continuous task adaptation (SPIRF-CTA). The SPIRF-CTA approach enables the constructed model to identify and focus on the most important parameters for the current task by designing a normalized parameter importance selection mechanism and a loss function with parameter importance penalties, and it adjusts the parameter updates by incorporating Hessian matrix information to achieve reasonable forgetting and prevent the new task from completely overwriting the knowledge of the previous task. Moreover, we design a model alignment loss function and a multitask loss function to use the knowledge of the new and previous tasks. We evaluate the SPIRF-CTA method on the Split CIFAR-10 Split CIFAR-100, and Split mini-ImageNet datasets, and the results show that the image classification accuracies of the proposed approach improve by 3.6%, 4.4%, and 3.36%, respectively; moreover, the SPIRF-CTA method exhibits excellent control of the degree of forgetting, with a forgetting rate of only 3.54%. Code is available at https://github.com/ybyangjing/CTA.

A study of Rural women’s financial literacy and awareness level towards financial products and services in Kerala perspective with Special reference to Malappuram District

Financial literacy is crucial in empowering individuals, particularly rural women, to make informed financial decisions and achieve economic well-being. This study explores the financial literacy and awareness levels of rural women in the Malappuram district, focusing on the relationship between socio-demographic factors and financial literacy. The research, conducted through a cross-sectional descriptive study among 100 women, reveals that most respondents are young, educated, and possess a moderate level of awareness and knowledge of financial tasks and products. The study highlights significant barriers to financial literacy, including social and cultural issues, lack of education, income constraints, and gender discrimination. Despite these challenges, the penetration of financial products like bank accounts, debit cards, and mobile banking is relatively high among the participants. The study finds a significant relationship between age and financial literacy but no significant correlation between education or income levels and financial literacy awareness. The findings underscore the need for targeted financial education programs to enhance financial literacy among rural women, addressing identified barriers and focusing on age-specific strategies to improve their economic participation and contribute to national economic development.

Augmentation-aware self-supervised learning with conditioned projector

Self-supervised learning (SSL) is a powerful technique for learning from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo can reach quality on par with supervised approaches. However, this invariance may be detrimental for solving downstream tasks that depend on traits affected by augmentations used during pretraining, such as color. In this paper, we propose to foster sensitivity to such characteristics in the representation space by modifying the projector network, a common component of self-supervised architectures. Specifically, we supplement the projector with information about augmentations applied to images. For the projector to take advantage of this auxiliary conditioning when solving the SSL task, the feature extractor learns to preserve the augmentation information in its representations. Our approach, coined Conditional Augmentation-aware Self-supervised Learning (CASSLE), is directly applicable to typical joint-embedding SSL methods regardless of their objective functions. Moreover, it does not require major changes in the network architecture or prior knowledge of downstream tasks. In addition to an analysis of sensitivity towards different data augmentations, we conduct a series of experiments, which show that CASSLE improves over various SSL methods, reaching state-of-the-art performance in multiple downstream tasks. 11We make our codebase available at https://github.com/gmum/CASSLE.22The supplementary material of this paper was shared separately due to page count limit (see Appendix A). The entire paper, along with the supplementary material, can also be accessed at https://arxiv.org/abs/2306.06082.33A short version of this paper appeared at the NeurIPS 2023 Workshop: Self-Supervised Learning-Theory and Practice (https://sslneurips23.github.io).

Metamotivational task knowledge of performance-approach and performance-avoidance achievement goals

Metamotivational task knowledge of performance-approach and performance-avoidance achievement goals

Multi-swarm multi-tasking ensemble learning for multi-energy demand prediction

The increasing uptake of renewable energy sources leads to more uncertainties of energy scheduling, resulting in more difficulties of energy demand management in smart grid. Accurate forecasting plays a significant role in energy management, and in some cases it may involve predictions of different consumers or geographic regions. Traditionally, these prediction problems have been solved independently, ignoring the potential shared knowledge among them that may help facilitate the overall performance. In this manuscript, we propose a multi-swarm multi-tasking ensemble learning (MSMTEL) framework for solving the energy demand forecasting across multiple cities. The proposed method comprises single-task pretraining, multi-task optimization (MTO), and ensemble learning (EL). For each prediction task, several subtasks are generated based on predefined parameters in the forecasting model. Each subtask utilizes an independent deep neural network (DNN) as the predictor, which is pretrained individually. Subsequently, we modify the dynamic multi-swarm particle swarm optimization (DMS-PSO) as a customized multi-swarm PSO (CMS-PSO) algorithm for implementing MTO. Each subswarm in CMS-PSO focuses on finding the optimal model knowledge (pretrained DNN weights and biases) of source tasks (all subtasks) to be reused by the target subtask. Finally, instead of choosing the best forecasting among the subtasks, results of subtasks over the same energy prediction problem are combined to yield the EL result, wherein weight coefficients determining the contributions of subtasks to EL are optimized by PSO. MSMTEL is evaluated against single-task learning (STL) and MTO to demonstrate its superior performance.

Development of a method for refining recommendations using temporal knowledge in individual insurance tasks

The subject of the research is the process of constructing recommendations in individual insurance tasks. The aim is to develop an approach for building recommendations in personalized insurance projects using temporal knowledge to adapt proposed insurance plans according to client behavior on insurance company websites. Objectives: to structure temporal rules considering the peculiarities of the online insurance recommendation process; to develop a method for constructing recommendations for insurance product selection using temporal knowledge. Conclusions: temporal rules have been structured for the task of building recommendations in personalized insurance projects. These rules generalize behavior in relative time for multiple users, enabling the generalization of user action sequences. A method for constructing online recommendations using temporal knowledge has been developed. The method consists of two phases: temporal knowledge formation and recommendation construction. The first phase is performed offline and is designed to form a base of temporal rules that generalize knowledge about user behavior. The second phase is executed online and involves refining and further utilizing temporal rules to adapt recommendations according to current user behavior. The method enables prompt adaptation of recommendations considering the user's current actions, creating conditions for increasing user trust in the recommender system's proposals.

Enhanced “learning to learn” through a hierarchical dual-learning system: the case of action video game players

In contrast to conventional cognitive training paradigms, where learning effects are specific to trained parameters, playing action video games has been shown to produce broad enhancements in many cognitive functions. These remarkable generalizations challenge the conventional theory of generalization that learned knowledge can be immediately applied to novel situations (i.e., immediate generalization). Instead, a new “learning to learn” theory has recently been proposed, suggesting that these broad generalizations are attained because action video game players (AVGPs) can quickly acquire the statistical regularities of novel tasks in order to increase the learning rate and ultimately achieve better performance. Although enhanced learning rate has been found for several tasks, it remains unclear whether AVGPs efficiently learn task statistics and use learned task knowledge to guide learning. To address this question, we tested 34 AVGPs and 36 non-video game players (NVGPs) on a cue-response associative learning task. Importantly, unlike conventional cognitive tasks with fixed task statistics, in this task, cue-response associations either remain stable or change rapidly (i.e., are volatile) in different blocks. To complete the task, participants should not only learn the lower-level cue-response associations through explicit feedback but also actively estimate the high-level task statistics (i.e., volatility) to dynamically guide lower-level learning. Such a dual learning system is modelled using a hierarchical Bayesian learning framework, and we found that AVGPs indeed quickly extract the volatility information and use the estimated higher volatility to accelerate learning of the cue-response associations. These results provide strong evidence for the “learning to learn” theory of generalization in AVGPs. Taken together, our work highlights enhanced hierarchical learning of both task statistics and cognitive abilities as a mechanism underlying the broad enhancements associated with action video game play.

Factors influencing readiness to implement digital audit among internal auditors of the Malaysian public sector

PurposeThis paper aims to examine the factors that influence the readiness of public sector internal auditors of the Accountant General’s Department (AGD) in Malaysia to implement digital audit.Design/methodology/approachThis study used an online questionnaire survey that was administered to a population of 124 internal auditors of the AGD, Malaysia. The readiness was measured in two ways: change commitment (CCOM) and change efficacy (CEFF), whereas the predictors of readiness encompass three factors: change valence, task knowledge and task availability. A partial least squares modelling using the SmartPLS 4 version was used to test the hypotheses.FindingsThe results reveal that change valence, task knowledge and task availability are positively significant factors influencing the CCOM of the AGD to implement digital audit. However, change valence is the only factor influencing CEFF.Originality/valueThis study offers useful empirical evidence on determinants of readiness to implement digital audit among internal auditors in the public sector, which is crucial towards supporting the Malaysian Government’s digital transformation agenda.

Enhancing Clinical Relevance of Pretrained Language Models Through Integration of External Knowledge: Case Study on Cardiovascular Diagnosis From Electronic Health Records.

Despite their growing use in health care, pretrained language models (PLMs) often lack clinical relevance due to insufficient domain expertise and poor interpretability. A key strategy to overcome these challenges is integrating external knowledge into PLMs, enhancing their adaptability and clinical usefulness. Current biomedical knowledge graphs like UMLS (Unified Medical Language System), SNOMED CT (Systematized Medical Nomenclature for Medicine-Clinical Terminology), and HPO (Human Phenotype Ontology), while comprehensive, fail to effectively connect general biomedical knowledge with physician insights. There is an equally important need for a model that integrates diverse knowledge in a way that is both unified and compartmentalized. This approach not only addresses the heterogeneous nature of domain knowledge but also recognizes the unique data and knowledge repositories of individual health care institutions, necessitating careful and respectful management of proprietary information. This study aimed to enhance the clinical relevance and interpretability of PLMs by integrating external knowledge in a manner that respects the diversity and proprietary nature of health care data. We hypothesize that domain knowledge, when captured and distributed as stand-alone modules, can be effectively reintegrated into PLMs to significantly improve their adaptability and utility in clinical settings. We demonstrate that through adapters, small and lightweight neural networks that enable the integration of extra information without full model fine-tuning, we can inject diverse sources of external domain knowledge into language models and improve the overall performance with an increased level of interpretability. As a practical application of this methodology, we introduce a novel task, structured as a case study, that endeavors to capture physician knowledge in assigning cardiovascular diagnoses from clinical narratives, where we extract diagnosis-comment pairs from electronic health records (EHRs) and cast the problem as text classification. The study demonstrates that integrating domain knowledge into PLMs significantly improves their performance. While improvements with ClinicalBERT are more modest, likely due to its pretraining on clinical texts, BERT (bidirectional encoder representations from transformer) equipped with knowledge adapters surprisingly matches or exceeds ClinicalBERT in several metrics. This underscores the effectiveness of knowledge adapters and highlights their potential in settings with strict data privacy constraints. This approach also increases the level of interpretability of these models in a clinical context, which enhances our ability to precisely identify and apply the most relevant domain knowledge for specific tasks, thereby optimizing the model's performance and tailoring it to meet specific clinical needs. This research provides a basis for creating health knowledge graphs infused with physician knowledge, marking a significant step forward for PLMs in health care. Notably, the model balances integrating knowledge both comprehensively and selectively, addressing the heterogeneous nature of medical knowledge and the privacy needs of health care institutions.

Backdoor attacks on unsupervised graph representation learning

Unsupervised graph learning techniques have garnered increasing interest among researchers. These methods employ the technique of maximizing mutual information to generate representations of nodes and graphs. We show that these methods are susceptible to backdoor attacks, wherein the adversary can poison a small portion of unlabeled graph data (e.g., node features and graph structure) by introducing triggers into the graph. This tampering disrupts the representations and increases the risk to various downstream applications. Previous backdoor attacks in supervised learning primarily operate directly on the label space and may not be suitable for unlabeled graph data. To tackle this challenge, we introduce GRBA,11https://github.com/fbd3/GRBA.git. a gradient-based first-order backdoor attack method. To the best of our knowledge, this constitutes a pioneering endeavor in investigating backdoor attacks within the domain of unsupervised graph learning. The initiation of this method does not necessitate prior knowledge of downstream tasks, as it directly focuses on representations. Furthermore, it is versatile and can be applied to various downstream tasks, including node classification, node clustering and graph classification. We evaluate GRBA on state-of-the-art unsupervised learning models, and the experimental results substantiate the effectiveness and evasiveness of GRBA in both node-level and graph-level tasks.

Engaging undergraduate students in preprint peer review

Authentic assessment allows students to demonstrate knowledge and skills in real-world tasks. In research, peer review is one such task that researchers learn by doing, as they evaluate other researchers’ work. This means peer review could serve as an authentic assessment that engages students’ critical thinking skills in a process of active learning. In this study, we had students write peer reviews of preprints, scaffolded by a rubric. Agreement between the students and academics was reasonable, and active student involvement was high. The results suggest that use of peer review in undergraduate classes should be explored more. It likely facilitates students’ ability to evaluate the quality of scientific studies, encourages active learning about the scientific process and shows potential for contributing to publicly-available assessment of scientific studies.

Lingdan: enhancing encoding of traditional Chinese medicine knowledge for clinical reasoning tasks with large language models.

The recent surge in large language models (LLMs) across various fields has yet to be fully realized in traditional Chinese medicine (TCM). This study aims to bridge this gap by developing a large language model tailored to TCM knowledge, enhancing its performance and accuracy in clinical reasoning tasks such as diagnosis, treatment, and prescription recommendations. This study harnessed a wide array of TCM data resources, including TCM ancient books, textbooks, and clinical data, to create 3 key datasets: the TCM Pre-trained Dataset, the Traditional Chinese Patent Medicine (TCPM) Question Answering Dataset, and the Spleen and Stomach Herbal Prescription Recommendation Dataset. These datasets underpinned the development of the Lingdan Pre-trained LLM and 2 specialized models: the Lingdan-TCPM-Chat Model, which uses a Chain-of-Thought process for symptom analysis and TCPM recommendation, and a Lingdan Prescription Recommendation model (Lingdan-PR) that proposes herbal prescriptions based on electronic medical records. The Lingdan-TCPM-Chat and the Lingdan-PR Model, fine-tuned on the Lingdan Pre-trained LLM, demonstrated state-of-the art performances for the tasks of TCM clinical knowledge answering and herbal prescription recommendation. Notably, Lingdan-PR outperformed all state-of-the-art baseline models, achieving an improvement of 18.39% in the Top@20 F1-score compared with the best baseline. This study marks a pivotal step in merging advanced LLMs with TCM, showcasing the potential of artificial intelligence to help improve clinical decision-making of medical diagnostics and treatment strategies. The success of the Lingdan Pre-trained LLM and its derivative models, Lingdan-TCPM-Chat and Lingdan-PR, not only revolutionizes TCM practices but also opens new avenues for the application of artificial intelligence in other specialized medical fields. Our project is available at https://github.com/TCMAI-BJTU/LingdanLLM.

Augmenting clinicians' analytical workflow through task-based integration of data visualizations and algorithmic insights: a user-centered design study.

To understand healthcare providers' experiences of using GlucoGuide, a mockup tool that integrates visual data analysis with algorithmic insights to support clinicians' use of patientgenerated data from Type 1 diabetes devices. This qualitative study was conducted in three phases. In Phase 1, 11 clinicians reviewed data using commercial diabetes platforms in a think-aloud data walkthrough activity followed by semistructured interviews. In Phase 2, GlucoGuide was developed. In Phase 3, the same clinicians reviewed data using GlucoGuide in a think-aloud activity followed by semistructured interviews. Inductive thematic analysis was used to analyze transcripts of Phase 1 and Phase 3 think-aloud activity and interview. 3 high level tasks, 8 sub-tasks, and 4 challenges were identified in Phase 1. In Phase 2, 3 requirements for GlucoGuide were identified. Phase 3 results suggested that clinicians found GlucoGuide easier to use and experienced a lower cognitive burden as compared to the commercial diabetes data reports that were used in Phase 1. Additionally, GlucoGuide addressed the challenges experienced in Phase 1. The study suggests that the knowledge of analytical tasks and task-specific visualization strategies in implementing features of data interfaces can result in tools that lower the perceived burden of engaging with data. Additionally, supporting clinicians in contextualizing algorithmic insights by visual analysis of relevant data can positively influence clinicians' willingness to leverage algorithmic support. Task-aligned tools that combine multiple data-driven approaches, such as visualization strategies and algorithmic insights, can improve clinicians' experience in reviewing device data.

Reinforcement learning with predefined and inferred reward machines in stochastic games

This paper focuses on Multi-Agent Reinforcement Learning (MARL) in non-cooperative stochastic games, particularly addressing the challenge of task completion characterized by non-Markovian reward functions. We employ Reward Machines (RMs) to incorporate high-level task knowledge. Firstly, we introduce Q-learning with Reward Machines for Stochastic Games (QRM-SG), where RMs are predefined and available to agents. QRM-SG learns each agent’s best-response policy at Nash equilibrium by defining the Q-function in augmented state space that integrates the stochastic game and RM states. The Lemke-Howson method is utilized to compute the best-response policies for the stage game defined by the current Q-functions at each time step. Subsequently, we explore a more challenging scenario where RMs are unavailable and propose Multi-Agent Reinforcement learning with Concurrent High-level knowledge inference (MARCH). MARCH uses automata learning to learn RMs iteratively and combines this process with QRM-SG for learning the best-response policies. The RL episodes where the obtained rewards are inconsistent with the rewards from the current RMs trigger the inference of new RMs. We prove QRM-SG and MARCH converge to the best-response policies under certain conditions. Two scenarios are conducted to demonstrate the superior performance of QRM-SG and MARCH compared to baseline methods.

Integrating Domain Knowledge in Multi-Source Classification Tasks

This work presents an extended investigation into multi-domain learning techniques within the context of image and audio classification, with a focus on the latter. In machine learning, collections of data obtained or generated under similar conditions are referred to as domains or data sources. However, the distinct acquisition or generation conditions of these data sources are often overlooked, despite their potential to significantly impact model generalization. Multi-domain learning addresses this challenge by seeking effective methods to train models to perform adequately across all domains seen during the training process. Our study explores a range of model-agnostic multi-domain learning techniques that leverage explicit domain information alongside class labels. Specifically, we delve into three distinct methodologies: a general approach termed Stew, which involves mixing all available data indiscriminately; and two batch domain-regularization methods: Balanced Domains and Loss Sum. These methods are evaluated through several experiments conducted on datasets featuring multiple data sources for audio and image classification tasks. Our findings underscore the importance of considering domain-specific information during the training process. We demonstrate that the application of the Loss Sum method yields notable improvements in model performance (0.79 F1-Score) compared to conventional approaches that blend data from all available domains (0.62 F1-Score). By examining the impact of different multi-domain learning techniques on classification tasks, this study contributes to a deeper understanding of effective strategies for leveraging domain knowledge in machine learning model training.

Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review

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.