Consistent Labeling Research Articles

Consistency-guided Multi-Source-Free Domain Adaptation

Deep neural networks suffer from severe performance degradation when facing a distribution shift between the labeled source domain and unlabeled target domain. Domain adaptation addresses this issue by aligning the feature distributions of both domains. Conventional methods assume that the labeled source samples are drawn from a single data distribution (domain) and can be fully accessed during training. However, in real applications, multiple source domains with different distributions often exist, and source samples may be unavailable due to privacy and storage constraints. To address multi-source and data-free challenges, Multi-Source-Free Domain Adaptation (MSFDA) uses only diverse pre-trained source models without requiring any source data. Most existing MSFDA methods adapt each source model to the target domain individually, making them ineffective in leveraging the complementary transferable knowledge from different source models. In this paper, we propose a novel COnsistency-guided multi-source-free Domain Adaptation (CODA) method, which leverages the label consistency criterion as a bridge to facilitate the cooperation among source models. CODA applies consistency regularization on the soft labels of weakly- and strongly-augmented target samples from each pair of source models, allowing them to supervise each other. To achieve high-quality pseudo-labels, CODA also performs a consistency-based denoising to unify the pseudo-labels from different source models. Finally, CODA optimally combines different source models by maximizing the mutual information of the predictions of the resulting target model. Extensive experiments on four benchmark datasets demonstrate the effectiveness of CODA compared to the state-of-the-art methods.

Agent-DA: Enhancing low-resource event extraction with collaborative multi-agent data augmentation

Low-resource event extraction presents a significant challenge in real-world applications, particularly in domains like pharmaceuticals, military and law, where data is frequently insufficient. Data augmentation, as a direct method for expanding samples, is considered an effective solution. However, existing data augmentation methods often suffers from text fluency issues and label hallucination. To address these challenges, we propose a framework called Agent-DA, which leverages multi-agent collaboration for event extraction data augmentation. Specifically, Agent-DA follows a three-step process: data generation by the large language model, collaborative filtering by both the large language model and small language model to discriminate easy samples, and the use of an adjudicator to identify hard samples. Through iterative and selective augmentation, our method significantly enhances both the quantity and quality of event samples, improving text fluency and label consistency. Extensive experiments on the ACE2005-EN and ACE2005-EN+ datasets demonstrate the effectiveness of Agent-DA, with F1-score improvements ranging from 0.15% to 16.18% in trigger classification and from 2.2% to 15.67% in argument classification. The code and models can be found at https://github.com/GYK-CASIC/Agent-DA.

Distributed multi-object tracking under limited field of view heterogeneous sensors with density clustering

We consider the problem of tracking multiple, unknown, and time-varying numbers of objects using a distributed network of heterogeneous sensors. In an effort to derive a formulation for practical settings, we consider limited and unknown sensor field-of-views (FoVs), sensors with limited local computational resources and communication channel capacity. The resulting distributed multi-object tracking algorithm involves solving an NP-hard multidimensional assignment problem either optimally for small-size problems or sub-optimally for general practical problems. For general problems, we propose an efficient distributed multi-object tracking algorithm that performs track-to-track fusion using a clustering-based analysis of the state space transformed into a density space to mitigate the complexity of the assignment problem. The proposed algorithm can more efficiently group local track estimates for fusion than existing approaches. To ensure we achieve globally consistent identities for tracks across a network of nodes as objects move between FoVs, we develop a graph-based algorithm to achieve label consensus and minimise track segmentation. Numerical experiments with synthetic and real-world trajectory datasets demonstrate that our proposed method is significantly more computationally efficient than state-of-the-art solutions, achieving similar tracking accuracy and bandwidth requirements but with improved label consistency.

A multi-slice attention fusion and multi-view personalized fusion lightweight network for Alzheimer’s disease diagnosis

ObjectiveAlzheimer’s disease (AD) is a type of neurological illness that significantly impacts individuals’ daily lives. In the intelligent diagnosis of AD, 3D networks require larger computational resources and storage space for training the models, leading to increased model complexity and training time. On the other hand, 2D slices analysis may overlook the 3D structural information of MRI and can result in information loss.ApproachWe propose a multi-slice attention fusion and multi-view personalized fusion lightweight network for automated AD diagnosis. It incorporates a multi-branch lightweight backbone to extract features from sagittal, axial, and coronal view of MRI, respectively. In addition, we introduce a novel multi-slice attention fusion module, which utilizes a combination of global and local channel attention mechanism to ensure consistent classification across multiple slices. Additionally, a multi-view personalized fusion module is tailored to assign appropriate weights to the three views, taking into account the varying significance of each view in achieving accurate classification results. To enhance the performance of the multi-view personalized fusion module, we utilize a label consistency loss to guide the model’s learning process. This encourages the acquisition of more consistent and stable representations across all three views.Main resultsThe suggested strategy is efficient in lowering the number of parameters and FLOPs, with only 3.75M and 4.45G respectively, and accuracy improved by 10.5% to 14% in three tasks. Moreover, in the classification tasks of AD vs. CN, AD vs. MCI and MCI vs. CN, the accuracy of the proposed method is 95.63%, 86.88% and 85.00%, respectively, which is superior to the existing methods.ConclusionsThe results show that the proposed approach not only excels in resource utilization, but also significantly outperforms the four comparison methods in terms of accuracy and sensitivity, particularly in detecting early-stage AD lesions. It can precisely capture and accurately identify subtle brain lesions, providing crucial technical support for early intervention and treatment.

LG-AKD: Application of a lightweight GCN model based on adversarial knowledge distillation to skeleton action recognition

Human action recognition, a pivotal topic in computer vision, is a highly complex and challenging task. It requires the analysis of not only spatial dependencies of targets but also temporal changes in these targets. In recent decades, the advancement of deep learning has led to the development of numerous action recognition methods based on deep neural networks. Given that the skeleton points of the human body can be treated as a graph structure, graph neural networks (GNNs) have emerged as an effective tool for modeling such data, garnering significant interest from researchers. This paper aims to address the issue of low test speed caused by over-complicated deep graph convolutional models. To achieve this, we compress the network structure using knowledge distillation from a teacher-student architecture, leading to a compact and lightweight student GNN. To enhance the model’s robustness and generalization capabilities, we introduce a data augmentation mechanism that generates diverse action sequences while maintaining consistent behavior labels, thereby providing a more comprehensive learning basis for the model. The proposed model integrates three distinct knowledge learning paths: teacher networks, original datasets, and derived data. The fusion of knowledge distillation and data augmentation enables lightweight student networks to outperform their teacher networks in terms of both performance and efficiency. Experimental results demonstrate the efficacy of our approach in the context of skeleton-based human action recognition, highlighting its potential to simplify state-of-the-art models while enhancing their performance.

Multi-view clustering via double spaces structure learning and adaptive multiple projection regression learning

Multi-view clustering aims to group objects with high similarity into one group according to the heterogeneous features of different views. The graph-based clustering methods have obtained excellent results. However, there remain a few common drawbacks. For example, some methods do not consider graphs' high-order structure information. Thus, fuller data information cannot be obtained. In addition, some methods remove noise, outliers, and redundant information in the graph learning phase, resulting in the loss of graph information. Furthermore, using predefined graphs cannot exploit complementary information between views. A triple strategy-based multi-view clustering method is presented to solve the above issues. First, Laplacian graphs are used for fusion learning, and the underlying first-order and second-order structure information among views are explored simultaneously. Then, a label fusion scheme is designed to eliminate noise, outliers, and redundant information and to mine the intrinsic characteristics of data labels. Besides, the consistent label matrix in adaptive regression learning is used to explore complementary information between views in a mutually guided learning way. Finally, the objective function is solved by using an efficient iterative method. Six types of experiments are conducted on eleven real-world multi-view datasets, and the conclusions that can be drawn are: (1) the proposed algorithm achieves the best results in terms of clustering accuracy on ten datasets with an average accuracy improvement of 5.11% compared to other algorithms. Specifically, the accuracy improved by 9.05% on dataset HW and 10.95% on dataset Reuters compared to the second results; (2) The ablation experiments confirm that the different learning strategies included in the proposed algorithm allow it to achieve better clustering performance.

Improved whole-mount immunofluorescence protocol for consistent and robust labeling of adult Drosophila melanogaster adipose tissue.

Energy storage and endocrine functions of the Drosophila fat body make it an excellent model for elucidating mechanisms that underlie physiological and pathophysiological organismal metabolism. Combined with Drosophila's robust genetic and immunofluorescence microscopy toolkits, studies of Drosophila fat body function are ripe for cell biological analysis. Unlike the larval fat body, which is easily removed as a single, cohesive sheet of tissue, isolating intact adult fat body proves to be more challenging, thus hindering consistent immunofluorescence labeling even within a single piece of adipose tissue. Here, we describe an improved approach to handling Drosophila abdomens that ensures full access of the adult fat body to solutions generally used in immunofluorescence labeling protocols. In addition, we assess the quality of fluorescence reporter expression and antibody immunoreactivity in response to variations in fixative type, fixation incubation time, and detergent used for cellular permeabilization. Overall, we provide several recommendations for steps in a whole-mount staining protocol that results in consistent and robust immunofluorescence labeling of the adult Drosophila fat body.

Semi-Supervised Learning for Multi-View Data Classification and Visualization

Data visualization has several advantages, such as representing vast amounts of data and visually demonstrating patterns within it. Manifold learning methods help us estimate lower-dimensional representations of data, thereby enabling more effective visualizations. In data analysis, relying on a single view can often lead to misleading conclusions due to its limited perspective. Hence, leveraging multiple views simultaneously and interactively can mitigate this risk and enhance performance by exploiting diverse information sources. Additionally, incorporating different views concurrently during the graph construction process using interactive visualization approach has improved overall performance. In this paper, we introduce a novel algorithm for joint consistent graph construction and label estimation. Our method simultaneously constructs a unified graph and predicts the labels of unlabeled samples. Furthermore, the proposed approach estimates a projection matrix that enables the prediction of labels for unseen samples. Moreover, it incorporates the information in the label space to further enhance the accuracy. In addition, it merges the information in different views along with the labels to construct a consensus graph. Experimental results conducted on various image databases demonstrate the superiority of our fusion approach compared to using a single view or other fusion algorithms. This highlights the effectiveness of leveraging multiple views and simultaneously constructing a unified graph for improved performance in data classification and visualization tasks in semi-supervised contexts.

Partial label feature selection via label disambiguation and neighborhood mutual information

Partial label learning aims to learn from training instances, each of which is associated with a set of candidate labels but only one is a ground-truth label. Feature selection is an effective method to improve the generalization capability of the learning model; however, partial label feature selection work is exceptionally challenging due to the limitation and ambiguity of label information. Therefore, this paper proposes a partial label feature selection algorithm based on label disambiguation and neighborhood mutual information. Firstly, neighborhood granularity is utilized to determine the neighborhoods of instances to disambiguate the candidate labels. Secondly, based on label confidence induced by disambiguation, feature relevance and redundancy are measured by neighborhood mutual information, which avoids the negative impact of data discretization on feature selection and directly handles continuous features. Concurrently, the kappa coefficient is employed to estimate the label consistency for describing the influences of feature changes on the label space. Then, the significance of each feature is evaluated by fusing feature relevance, feature redundancy, and label consistency. Finally, the effectiveness of the proposed algorithm is verified by comparing the proposed algorithm with four base classifiers and other feature selection methods. Furthermore, the feasibility of the proposed disambiguation method is demonstrated through comparison with four state-of-the-art disambiguation methods.

IML-SSOD: Interconnected and multi-layer threshold learning for semi-supervised detection

While semi-supervised anchored detector of the R-CNN series has achieved remarkable success, semi-supervised anchor-free detector lacks the ability to generate high-quality flexible pseudo labels, resulting in serious inconsistencies in SSOD. In order to make the network learn more reliable and consistent label data to solve the problem of information bias, we propose an interconnected and multi-layer threshold learning for semi-supervised object detection (IML-SSOD). The Joint Guided Estimation (JGE) module uses the Core Zone refinement module to improve the position accuracy score of low semantic information, and combines the classification and the centerness score as evaluation criteria to predict stable labels. The multi-layer threshold filtering method selects more potential label samples for the student network ensuring the information used in training. Extensive experiments on MS COCO and PASCAL VOC datasets demonstrated the effectiveness of IML-SSOD. Compared with existing methods, our method on VOC achieved 81.9% AP50 and 57.89% AP50:95, which is highly competitive.

Assessment of Medication Labeling Compliance in Outpatient Pharmacy: A Study in Riyadh, Saudi Arabia

Abstract This study assessed outpatient medication labels in 19 hospitals in Riyadh, Saudi Arabia, focusing on critical information necessary for safe and effective medication use. The study utilized a structured observation form based on guidelines from the Saudi Food and Drug Authority and the Institute for Safe Medication Practices. The form included indicators related to label identification, instructions, and layout. Compliance rates for each indicator were calculated, revealing varying levels of adherence across different hospitals. High compliance rates were observed for indicators such as the date of dispensing (100%), directions of use (100%), and typing directions in Arabic (100%). However, lower compliance rates were noted for physician and pharmacist information, drug information, and additional medication details, with rates ranging from 0 to 78.9%. Specifically, the inclusion of physician and pharmacist registration numbers had a compliance rate of 0%. The study highlighted significant gaps in standardizing medication labels, emphasizing the need for including essential information such as total quantity dispensed, number of refills, warning labels, medication indication, and storage conditions. Additionally, the use of barcodes, hospital logos, and Tallman letters was found to be inconsistent. In conclusion, the findings underscore the necessity for standardizing outpatient medication labeling practices to improve patient safety and medication management. This study calls for collaborative efforts, knowledge sharing, and the implementation of best practices to achieve consistent and accurate medication labeling in Saudi Arabia.

Age‐related off‐label drug prescribing in pediatric patients in South Korea and consistency of labeling compared to the United States, Europe, and Japan

AbstractInsufficient labeling information regarding the appropriate age for prescribing drugs to the pediatric population is challenging. This study aimed to analyze the off‐label prescription of age‐related drugs for pediatric patients using claims data from South Korea and to assess the consistency of the approved age in South Korea, the United States, Europe, and Japan. In 2020, 1004 unique drugs were prescribed to the pediatric population in South Korea. We found that 641 drugs (63.8%, p < 0.0001) were related to off‐label prescriptions for age‐related use at least once, and the total number of off‐label prescriptions was 2,236,669 (62.2%, p < 0.0001). Chlorpheniramine (28%) was the most frequently prescribed drug for pediatric patients with an age‐related off‐label, followed by budesonide (9%) and epinephrine (9%). The degree of agreement in the approved age range for 641 off‐label drugs across countries was assessed using the overall kappa coefficient. We observed slight agreement in labeling across all countries (κ: 0.16, 95% confidence interval [CI]: 0.14–0.18). The highest degree of agreement was observed between the United States and Europe (0.41, 0.37–0.45) due to pediatric‐population‐specific legislation. South Korea showed the lowest degree of agreement with the United States and Europe (0.10, 0.06–0.14). The United States, Europe, and Japan showed fair agreement (0.23, 0.21–0.26). However, the degree of agreement between South Korea, the United States, and Japan (0.09, 0.06–0.11) and South Korea, Europe, and Japan (0.08, 0.05–0.10) was low. This study highlights the need for South Korean regulatory agencies to consider introducing pediatric legislation to prescribe evidence‐based drugs for safe and effective use.

Improved STNNet, A benchmark for detection, tracking, and counting crowds using Drones

In computer vision, navigating multi-object tracking in crowded scenes poses a fundamental challenge with broad applications ranging from surveillance systems to autonomous vehicles. Traditional tracking methods encounter difficulties associating noisy object detections and maintaining consistent labels across frames, particularly in scenarios like video surveillance for crowd control and public safety. This paper introduces ’Improved Space-Time Neighbor-Aware Network (STNNet),’ an advanced framework for online Multi-Object Tracking (MOT) designed to address these challenges. Expanding upon the foundational STNNet architecture, our enhanced model incorporates deep reinforcement learning techniques to refine decision-making. By framing the online MOT problem as a Markov Decision Process (MDP), Improved STNNet learns a sophisticated policy for data association, adeptly handling complexities such as object birth/death and appearance/disappearance as state transitions within the MDP. Through extensive experimentation on benchmark datasets, including the MOT Challenge, our proposed Improved STNNet demonstrates superior performance, surpassing existing methods in demanding, crowded scenarios. This study showcases the effectiveness of our approach and lays the groundwork for advancing real-time video analysis applications, particularly in dynamic, crowded environments. Additionally, we utilize the dataset provided by STNNET for density map estimation, forming the basis for our research.•Develop an advanced framework for online Multi-Object Tracking (MOT) to address crowded scene challenges, particularly improving object association and label consistency across frames.•Explore integrating Deep Reinforcement learning techniques into the MOT framework, framing the problem as an MDP to refine decision-making and handle complexities such as object birth or death and appearance or disappearance transitions.

Improved DiOlistic labelling technique for neurons in situ: Detailed visualisation of dendritic spines and concurrent histochemical-detection in fixed tissue

DiOlistic labelling is a robust, unbiased ballistic method that utilises lipophilic dyes to morphologically label neurons. While its efficacy on freshly dissected tissue specimens is well-documented, applying DiOlistic labelling to stored, fixed brain tissue and its use in polychromatic multi-marker studies poses significant technical challenges. Here, we present an improved, step-by-step protocol for DiOlistic labelling of dendrites and dendritic spines in fixed mouse tissue. Our protocol encompasses the five key stages: Tissue Preparation, Dye Bullet Preparation, DiOlistic Labelling, Confocal Imaging, and Image Analysis. This method ensures reliable and consistent labelling of dendritic spines in fixed mouse tissue, combined with increased throughput of samples and multi-parameter staining and visualisation of tissue, thereby offering a valuable approach for neuroscientific research.

Standardizing imaging findings representation: harnessing Common Data Elements semantics and Fast Healthcare Interoperability Resources structures.

Designing a framework representing radiology results in a standards-based data structure using joint Radiological Society of North America/American College of Radiology Common Data Elements (CDEs) as the semantic labels on standard structures. This allows radiologist-created report data to integrate with artificial intelligence-generated results for use throughout downstream systems. We developed a framework modeling radiology findings as Health Level 7 (HL7) Fast Healthcare Interoperability Resources (FHIR) observations using CDE set/element identifiers as standardized semantic labels. This framework deploys CDE identifiers to specify radiology findings and attributes, providing consistent labels for radiology report concepts-diagnoses, recommendations, tabular/quantitative data-with built-in integration with RadLex, SNOMED CT, LOINC, and other ontologies. Observation structures fit within larger HL7 FHIR DiagnosticReport resources, providing output including both nuanced text and structured data. Labeling radiology findings as discrete data for interchange between systems requires two components: structure and semantics. CDE definitions provide semantic identifiers for findings and their component values. The FHIR observation resource specifies a structure for associating identifiers with radiology findings in the context of reports, with CDE-encoded observations referring to definitions for CDE identifiers in a central repository. The discussion includes an example of encoding pulmonary nodules on a chest CT as CDE-labeled observations, demonstrating the application of this framework to exchange findings throughout the imaging workflow, making imaging data available to downstream clinical systems. CDE-labeled observations establish a lingua franca for encoding, exchanging, and consuming radiology data at the level of individual findings, facilitating use throughout healthcare systems. CDE-labeled FHIR observation objects can increase the value of radiology results by facilitating their use throughout patient care.

Effects of Genotype and Growing Year on the Nutritional Composition and Pasting Properties of Glabrous Canary Seed (Phalaris canariensis L.) Groat Flours.

Canary seed flour is a new food ingredient that the United States Food and Drug Administration (FDA) and Health Canada recently granted Generally Regarded as Safe (GRAS) status. Stability in nutritional composition and functional properties is an essential characteristic of food ingredients for consistency in nutritional quality and performance in processing. This work assessed the effect of genotypic and environmental variation on the nutritional (protein, starch, amylose, oil, dietary fiber, minerals and fat-soluble vitamins) and pasting (as measured in viscosity (peak, trough, breakdown, final, and setback), peak time, and pasting temperatures) properties of Canary seed. The samples included four Canary seed varieties grown in randomized complete block design experiments at one location for two growing seasons. In general, the nutritional composition of Canary seed flour was not affected by genotype, growing year, and their interaction except for starch content, which was significantly affected by the growing year (p < 0.0001), and iron content, which was affected by genotypic variation (p < 0.0001). The pasting properties of Canary seed flour were significantly (p < 0.001) affected by both genotypic and growing year variation but not their interaction. Our results suggest that the food industry should measure starch and iron content prior to processing to ensure consistency in nutritional labeling. Also, for those applications where starch pasting properties are essential, the manufacturer should consider measuring the RVA pasting viscosities for every batch of raw material. The results have provided the baseline knowledge of which nutritional or functional properties of Canary seed flour can be improved through breeding and agronomy programs to ensure the reliability of Canary seed as an ingredient.

PFDup: Practical Fuzzy Deduplication for Encrypted Multimedia Data

Redundant data wastes cloud storage space, especially the multimedia data which comprises a large number of similar files and accounts for the majority of cloud storage. To protect privacy and eliminate redundancy in the cloud, fuzzy deduplication for encrypted multimedia data is practical and feasible. Unfortunately, existing fuzzy deduplications depend on aided server to be against security threats. In this paper, we propose a Practical Fuzzy Deduplication (PFDup) algorithm for encrypted multimedia data and it is secure against brute-force guessing attacks without additional independent severs. With our secure fuzzy deduplication technology, cloud storage can be significantly optimized by using Perceptual Hash (phash) to eliminate large quantities of identical even the similar multimedia data in a secure manner. In addition, PFDup protocol supports label consistency and a non-interactive Proof of Ownership (PO) in order to prevent the server–client collusion attacks. We conduct a series of experiments on numerous real-world datasets and the simulation results show that our deduplication rate for the similar images is over 91.5%.

Data Sorting Influence on Short Text Manual Labeling Quality for Hierarchical Classification

The precise categorization of brief texts holds significant importance in various applications within the ever-changing realm of artificial intelligence (AI) and natural language processing (NLP). Short texts are everywhere in the digital world, from social media updates to customer reviews and feedback. Nevertheless, short texts’ limited length and context pose unique challenges for accurate classification. This research article delves into the influence of data sorting methods on the quality of manual labeling in hierarchical classification, with a particular focus on short texts. The study is set against the backdrop of the increasing reliance on manual labeling in AI and NLP, highlighting its significance in the accuracy of hierarchical text classification. Methodologically, the study integrates AI, notably zero-shot learning, with human annotation processes to examine the efficacy of various data-sorting strategies. The results demonstrate how different sorting approaches impact the accuracy and consistency of manual labeling, a critical aspect of creating high-quality datasets for NLP applications. The study’s findings reveal a significant time efficiency improvement in terms of labeling, where ordered manual labeling required 760 min per 1000 samples, compared to 800 min for traditional manual labeling, illustrating the practical benefits of optimized data sorting strategies. Comparatively, ordered manual labeling achieved the highest mean accuracy rates across all hierarchical levels, with figures reaching up to 99% for segments, 95% for families, 92% for classes, and 90% for bricks, underscoring the efficiency of structured data sorting. It offers valuable insights and practical guidelines for improving labeling quality in hierarchical classification tasks, thereby advancing the precision of text analysis in AI-driven research. This abstract encapsulates the article’s background, methods, results, and conclusions, providing a comprehensive yet succinct study overview.

DATA FINDING, SHARING AND DUPLICATION REMOVAL IN THE CLOUD

Deduplication involves eliminating duplicate or redundant data to reduce stored data volume, commonly used in data backup, network optimization, and storage management. However, traditional deduplication methods have limitations with encrypted data and security. The primary objective of this project is to develop new distributed deduplication systems that offer increased reliability. In these systems, data chunks are distributed across the Hadoop Distributed File System (HDFS), and a robust key management system is utilized to ensure secure deduplication with slave nodes. Instead of having multiple copies of the same content, deduplication removes redundant data by retaining only one physical copy and referring other instances to that copy. The granularity of deduplication can vary, ranging from an entire file to a data block. The MD5 and 3DES algorithms are used to enhance the deduplication process. The proposed approach in this project is the Proof of Ownership (POF) of the file. With this method, deduplication can effectively address the issues of reliability and label consistency in HDFS storage systems. The proposed system has successfully reduced the cost and time associated with uploading and downloading data, while also optimizing storage space. Key Words: Cloud computing, data storage, file checksum algorithms, computational infrastructure, duplication.

Learning Real-World Image De-weathering with Imperfect Supervision

Real-world image de-weathering aims at removing various undesirable weather-related artifacts. Owing to the impossibility of capturing image pairs concurrently, existing real-world de-weathering datasets often exhibit inconsistent illumination, position, and textures between the ground-truth images and the input degraded images, resulting in imperfect supervision. Such non-ideal supervision negatively affects the training process of learning-based de-weathering methods. In this work, we attempt to address the problem with a unified solution for various inconsistencies. Specifically, inspired by information bottleneck theory, we first develop a Consistent Label Constructor (CLC) to generate a pseudo-label as consistent as possible with the input degraded image while removing most weather-related degradation. In particular, multiple adjacent frames of the current input are also fed into CLC to enhance the pseudo-label. Then we combine the original imperfect labels and pseudo-labels to jointly supervise the de-weathering model by the proposed Information Allocation Strategy (IAS). During testing, only the de-weathering model is used for inference. Experiments on two real-world de-weathering datasets show that our method helps existing de-weathering models achieve better performance. Code is available at https://github.com/1180300419/imperfect-deweathering.