Weak Supervision Research Articles

Analysis of Internal Control Management Problems in Hospital Finance and Accounting

This paper outlines the internal control management of hospital accounting and finance, introducing its concept, importance, and objectives. It then analyzes the problems existing in the internal control management of hospital accounting and finance, including an unsound management system, insufficient system implementation, inadequate risk assessment and control capabilities, poor information communication, weak internal supervision, and uneven personnel quality. The reasons for these problems are also analyzed, including outdated management concepts, irrational organizational structures, imperfect training and incentive mechanisms, low levels of information technology, and changes in the external environment. This paper proposes improvement measures for the internal control management of hospital accounting, including enhancing the management system, strengthening system implementation, improving risk assessment and control capabilities, enhancing the information communication mechanism, strengthening internal supervision, improving personnel quality, advancing information technology, and adapting to changes in the external environment.

Semantic segmentation of point clouds of ancient buildings based on weak supervision

Semantic segmentation of point clouds of ancient buildings plays an important role in Historical Building Information Modelling (HBIM). As the annotation task of point cloud of ancient architecture is characterised by strong professionalism and large workload, which greatly restricts the application of point cloud semantic segmentation technology in the field of ancient architecture, therefore, this paper launches a research on the semantic segmentation method of point cloud of ancient architecture based on weak supervision. Aiming at the problem of small differences between classes of ancient architectural components, this paper introduces a self-attention mechanism, which can effectively distinguish similar components in the neighbourhood. Moreover, this paper explores the insufficiency of positional encoding in baseline and constructs a high-precision point cloud semantic segmentation network model for ancient buildings—Semantic Query Network based on Dual Local Attention (SQN-DLA). Using only 0.1% of the annotations in our homemade dataset and the Architectural Cultural Heritage (ArCH) dataset, the mean Intersection over Union (mIoU) reaches 66.02% and 58.03%, respectively, which is an improvement of 3.51% and 3.91%, respectively, compared to the baseline.

Understanding the impact of climate change on critical infrastructure through nlp analysis of scientific literature

ABSTRACT Climate change is intensifying natural hazards, putting critical infrastructure systems at risk. The effects of climate change on critical infrastructure can be significant, and communities need to consider these risks when planning and designing infrastructure systems for the future. To that end, natural language processing (NLP) is a promising approach for analyzing large volumes of climate change and infrastructure-related scientific literature. To train a supervised model using NLP techniques, a significant subset of the corpus must be labeled into categories based on user-defined criteria, which is a time-consuming process. To expedite this process, we developed a weak supervision-based approach that leverages semantic similarity between categories and documents to generate category labels for the domain-specific corpus. In comparison with a months-long process of subject-matter expert labeling, we assign category labels to the whole corpus using weak supervision and supervised learning in 13 hours.

Rethink video retrieval representation for video captioning

Video captioning, a challenging task targeting the automatic generation of accurate and comprehensive descriptions based on video content, has witnessed substantial success recently driven by bridging video representations and textual semantics. Inspired by the nature of the video retrieval task, which learns visual features strongly related to text queries, we propose to take advantage of visual representation learning from the video retrieval framework to tackle video captioning tasks and construct adequate multi-grained cross-modal matching while extracting visual features. However, a simple direct application of recent video retrieval models fails to capture sufficient temporal details and the rich visual features of local patch tokens of video frames lack semantic information essential for captioning tasks. These deficiencies are primarily due to these models lack fine-grained interactions between video frames and offer only weak textual supervision over frame patch tokens. To increase the attention on temporal details, we propose a learnable token shift module, which flexibly captures subtle movements in local regions across the temporal sequence. Furthermore, we devise a Refineformer, which learns to integrate local video patch tokens strongly related to desired captions via a cross-attention mechanism. Extensive experiments on MSVD, MSR-VTT and VATEX demonstrate the favorable performance of our method. Code will be available at https://github.com/tiesanguaixia/IVRC.

Weakly Supervised AUC Optimization: A Unified Partial AUC Approach.

Since acquiring perfect supervision is usually difficult, real-world machine learning tasks often confront inaccurate, incomplete, or inexact supervision, collectively referred to as weak supervision. In this work, we present WSAUC, a unified framework for weakly supervised AUC optimization problems, which covers noisy label learning, positive-unlabeled learning, multi-instance learning, and semi-supervised learning scenarios. Within the WSAUC framework, we first frame the AUC optimization problems in various weakly supervised scenarios as a common formulation of minimizing the AUC risk on contaminated sets, and demonstrate that the empirical risk minimization problems are consistent with the true AUC. Then, we introduce a new type of partial AUC, specifically, the reversed partial AUC (rpAUC), which serves as a robust training objective for AUC maximization in the presence of contaminated labels. WSAUC offers a universal solution for AUC optimization in various weakly supervised scenarios by maximizing the empirical rpAUC. Theoretical and experimental results under multiple settings support the effectiveness of WSAUC on a range of weakly supervised AUC optimization tasks.

Multi-perspective feature collaborative perception learning network for non-destructive detection of pavement defects

Pavement defects detection has made significant progress with the development of convolutional neural networks. Due to the topological complexity of pavement defects regions, most existing detection methods are limited to a limited number of types of defects, which results in unsatisfactory detection results for multi-classified defects. Several studies have used enhanced data to address this issue, however, few have considered the inefficiency caused by imbalanced differences between classes from the perspective of the network model itself. In light of this issue, our goal is to fill this gap by better exploring the fusion of different feature information to improve the performance of the network. As a result, we propose a multi-perspective feature collaborative perception learning network (MFCPLNet), which uses the model's contextual information to guide high-quality multi-classified defects detection and that can be adapted to various pavement conditions. Specifically, for adaptive feature extraction, an irregular perceptual extraction network (IPENet) with enhanced edge information is first designed to draw upon hybrid deformable convolution for efficient network block hybridization. Additionally, a multi-balanced collaborative learning mechanism (MCLM) consisting of auxiliary axial information and 3D feature guidance is constructed to enhance deep semantic features, improve the localization of defects in defective regions, and compensate for weak category supervision. Lastly, in the detection head, an iterative soft aggregation module has been designed to enhance scalable spatial interactions. The results of extensive testing were based on publicly available pavement defects datasets. Based on the proposed network, the mAP index reaches 29.6% and 33.8%, respectively, an increase of 8.3% and 4.6% over the baseline, which is qualitatively and quantitatively superior to mainstream methods.

Mixed Supervision of Histopathology Improves Prostate Cancer Classification From MRI.

Non-invasive prostate cancer classification from MRI has the potential to revolutionize patient care by providing early detection of clinically significant disease, but has thus far shown limited positive predictive value. To address this, we present a image-based deep learning method to predict clinically significant prostate cancer from screening MRI in patients that subsequently underwent biopsy with results ranging from benign pathology to the highest grade tumors. Specifically, we demonstrate that mixed supervision via diverse histopathological ground truth improves classification performance despite the cost of reduced concordance with image-based segmentation. Where prior approaches have utilized pathology results as ground truth derived from targeted biopsies and whole-mount prostatectomy to strongly supervise the localization of clinically significant cancer, our approach also utilizes weak supervision signals extracted from nontargeted systematic biopsies with regional localization to improve overall performance. Our key innovation is performing regression by distribution rather than simply by value, enabling use of additional pathology findings traditionally ignored by deep learning strategies. We evaluated our model on a dataset of 973 (testing n=198 ) multi-parametric prostate MRI exams collected at UCSF from 2016-2019 followed by MRI/ultrasound fusion (targeted) biopsy and systematic (nontargeted) biopsy of the prostate gland, demonstrating that deep networks trained with mixed supervision of histopathology can feasibly exceed the performance of the Prostate Imaging-Reporting and Data System (PI-RADS) clinical standard for prostate MRI interpretation (71.6% vs 66.7% balanced accuracy and 0.724 vs 0.716 AUC).

Weakly Supervised Deep Learning in Radiology.

Deep learning (DL) is currently the standard artificial intelligence tool for computer-based image analysis in radiology. Traditionally, DL models have been trained with strongly supervised learning methods. These methods depend on reference standard labels, typically applied manually by experts. In contrast, weakly supervised learning is more scalable. Weak supervision comprises situations in which only a portion of the data are labeled (incomplete supervision), labels refer to a whole region or case as opposed to a precisely delineated image region (inexact supervision), or labels contain errors (inaccurate supervision). In many applications, weak labels are sufficient to train useful models. Thus, weakly supervised learning can unlock a large amount of otherwise unusable data for training DL models. One example of this is using large language models to automatically extract weak labels from free-text radiology reports. Here, we outline the key concepts in weakly supervised learning and provide an overview of applications in radiologic image analysis. With more fundamental and clinical translational work, weakly supervised learning could facilitate the uptake of DL in radiology and research workflows by enabling large-scale image analysis and advancing the development of new DL-based biomarkers.

Study on the Application of Internal Control in the Management of Urban Commercial Banks

In February 2021, Baoshang Bank, whose total asset size had exceeded 500 billion, exited the stage of history with more than 200 billion in unpayable debts. Now look back on its life, from the clouds fell to the bottom. However, there are traces of its causes. Weak supervision of funds, the organizational structure of the organization is a sham, excessive concentration of equity internal governance failure eventually became the key to its demise. Therefore, this paper will take the current situation of rising non‐ performing loan rate of urban commercial banks as the entry point to discuss the importance of internal governance and make suggestions for the establishment of a sound internal control system in urban commercial banks.

Analysis of Brondolan Fruit Loss in Palm Oil Harvesting Activities in the Case Study of Sentekan Estate PT Rea Kaltim Plantations

Brondolan is an oil palm fruit that is separated from spikelets because it is too ripe during harvesting activities. Apart from that, brondolan is part of the fresh fruit bunch which produces maximum quality Crude Palm Oil (CPO). The aim of this research is to analyze losses from harvesting activities in the form of oil palm fruit stalks. The research method is to carry out quantitative and descriptive analysis. Loss of brondolan fruit during palm oil harvesting activities from the research sample was 10% of the sample block area in the disk area, pickle market area and yield collection area (TPH), amounting to 16,946 Kg/month of the total Kg/division oil palm fruit production. This occurs because the fruit is abandoned or left behind as a result of weak supervision and poor maintenance or maintenance activities in the plate area, pickle market area and TPH area which are not controlled by the growth of weeds, kentosan, this has an impact on the potential loss of 3,2% of total TBS production in the division.

Leveraging Large Language Models for Knowledge-free Weak Supervision in Clinical Natural Language Processing.

The performance of deep learning-based natural language processing systems is based on large amounts of labeled training data which, in the clinical domain, are not easily available or affordable. Weak supervision and in-context learning offer partial solutions to this issue, particularly using large language models (LLMs), but their performance still trails traditional supervised methods with moderate amounts of gold-standard data. In particular, inferencing with LLMs is computationally heavy. We propose an approach leveraging fine-tuning LLMs and weak supervision with virtually no domain knowledge that still achieves consistently dominant performance. Using a prompt-based approach, the LLM is used to generate weakly-labeled data for training a downstream BERT model. The weakly supervised model is then further fine-tuned on small amounts of gold standard data. We evaluate this approach using Llama2 on three different n2c2 datasets. With no more than 10 gold standard notes, our final BERT models weakly supervised by fine-tuned Llama2-13B consistently outperformed out-of-the-box PubMedBERT by 4.7-47.9% in F1 scores. With only 50 gold standard notes, our models achieved close performance to fully fine-tuned systems.

Multi-view contextual adaptation network for weakly supervised object detection in remote sensing images

ABSTRACT Weakly supervised learning plays a pivotal role in the field of object detection, i.e. Weakly supervised object detection (WSOD), significantly reducing annotation costs relying on image-level labels. However, WSOD exhibits certain limitations. Typically, they tend to identify the most easily recognizable local regions within targets, posing challenges in accurately delineating the boundaries of targets. Moreover, the presence of multiple instances of the same class in adjacent locations complicates the effective distinction between multiple objects within the same category. On the other hand, the complex backgrounds and dense distribution of targets in remote sensing images (RSI) further exacerbate the difficulty of weakly supervised detection. To address the above issues, we propose a model termed the Multi-View Contextual Adaptation Network (VCANet). Building on the classic Online Instance Classifier Refinement (OICR) framework, we propose to incorporate an contextual adaptation perception, within a multi-view learning framework, and integrate a pseudo-label filtering process. The contextual adaptation perception utilizes the surrounding environment information to enhance localization capabilities, guiding the model to prioritize target objects by referring to their spatially neighbouring pixels. Multi-view learning manufactures additional constraints from diverse perspectives, thereby revealing objects that might be overlooked due to the weak supervision in a single view. The pseudo-label filtering process eliminates inaccurate pseudo-labels by identifying reliable foregrounds to mitigate overlapping proposals during the label propagation. On challenging datasets NWPU VHR-10.v2 and DIOR, we achieve promising results with mAP of 62.3% and 28.2%, respectively, surpassing existing benchmarks.

EFEKTIVITAS PEMUNGUTAN PAJAK PARKIR DI KOTA SAMARINDA: TINJAUAN DARI PERSPEKTIF HUKUM DAN KEBIJAKAN

Parking tax is a significant source of Local Revenue (PAD) in Samarinda City, but its implementation faces various challenges. The regulations governing parking tax aim to provide a clear legal framework, yet taxpayer compliance remains low. Weak supervision, limited technology, and low public awareness are the main factors hindering tax collection effectiveness. The use of digital technology in the parking system can enhance taxpayer compliance and reduce revenue leakage. Improving human resource capacity and conducting educational campaigns to raise public awareness are also important. Implementing policies that provide incentives for compliance and strict sanctions for violations is expected to optimize parking tax revenue and improve public services and city infrastructure.

Discriminative action tubelet detector for weakly-supervised action detection

We propose a novel framework for spatiotemporal action detection using only video-level class labels as weak supervision. Traditional fully-supervised approaches rely on labor-intensive manual annotation of bounding boxes for each frame. In contrast, collecting video-level class labels is significantly less tedious and more feasible compared to annotating frame-level sequences with bounding boxes. To address this challenge, we propose a discriminative action tubelet detector, called DAT-detector, designed to discern discriminative tubelets from action tubelet proposals (ATPs). Whereas the previous approaches have only focused on tubelet selection among the predefined object proposals, our DAT-detector prioritizes the generation of more precise action tubelets using regression and attention modules. Moreover, we introduce an ATP generation method that enhances the quality of tubelet proposals. Our approach achieves state-of-the-art performance on several benchmarks, and also demonstrates competitive performance even with fully-supervised approaches.

Faktor Penyebab dan Upaya Penanggulangan Penggunaan Bahan Peledak dalam Pencurian Ikan di Perairan Laut Sawu, Kabupaten Kupang

This study aims to determine and explain the factors causing the use of explosives in fish theft in the waters of the Sawu Sea, Kupang Regency and also to determine and explain the countermeasures against the use of explosives in fish theft in the waters of the Sawu Sea, Kupang Regency. This research is a qualitative study with empirical or sociological legal research methods and the object of research is causal factors and countermeasures. Data collection using interview techniques and literature study. The data analysis technique used is qualitative descriptive technique. The results of this study show that there are six factors causing the use of explosives in fish theft in the waters of the Sawu Sea, Kupang Regency, namely: (1) weak legal awareness factor, (2) motive factor, (3) weak economic factor, (4) weak law enforcement factor, (5) weak supervision factor, and (6) difficult to detect crime scene factor. Countermeasures carried out by the police and government agencies are premitive efforts, namely initial efforts made by competent government parties to provide appeals to avoid criminal acts. Preventive efforts are efforts made to provide prevention of community action both social problems and crime so as not to reach the threshold of disturbance and become a real disturbance. Repressive efforts are efforts made by competent parties when there has been a criminal offense or crime whose actions are in the form of law enforcement by imposing penalties.

From classification to segmentation with explainable AI: A study on crack detection and growth monitoring

Monitoring surface cracks in infrastructure is crucial for structural health monitoring. Automatic visual inspection offers an effective solution, especially in hard-to-reach areas. Machine learning approaches have proven their effectiveness but typically require large annotated datasets for supervised training. Once a crack is detected, monitoring its severity often demands precise segmentation of the damage. However, pixel-level annotation of images for segmentation is labor-intensive. To mitigate this cost, one can leverage explainable artificial intelligence (XAI) to derive segmentations from the explanations of a classifier, requiring only weak image-level supervision. This paper proposes applying this methodology to segment and monitor surface cracks. We evaluate the performance of various XAI methods and examine how this approach facilitates severity quantification and growth monitoring. Results reveal that while the resulting segmentation masks may exhibit lower quality than those produced by supervised methods, they remain meaningful and enable severity monitoring, thus reducing substantial labeling costs. Code and data available at https://github.com/EPFL-IMOS/crack-explanations.

Weakly Supervised Detection of Baby Cry

Detection of baby cry is an important part of baby monitoring. Almost all existing methods use supervised SVM, CNN, or their varieties. In this work, we propose to use weakly supervised anomaly detection to detect baby cry. In this weak supervision framework, we only need weak annotation if there is a cry in an audiofile. We design a data mining technique using the pre-trained VGGish feature extractor and an anomaly detection network on long untrimmed audiofiles. The obtained datasets are used to train a delicately designed super lightweight CNN for cry/non-cry classification. This CNN is then used as a feature extractor in an anomaly detection framework to achieve better cry detection performance.

A universal multiple instance learning framework for whole slide image analysis

BackgroundThe emergence of digital whole slide image (WSI) has driven the development of computational pathology. However, obtaining patch-level annotations is challenging and time-consuming due to the high resolution of WSI, which limits the applicability of fully supervised methods. We aim to address the challenges related to patch-level annotations. MethodsWe propose a universal framework for weakly supervised WSI analysis based on Multiple Instance Learning (MIL). To achieve effective aggregation of instance features, we design a feature aggregation module from multiple dimensions by considering feature distribution, instances correlation and instance-level evaluation. First, we implement instance-level standardization layer and deep projection unit to improve the separation of instances in the feature space. Then, a self-attention mechanism is employed to explore dependencies between instances. Additionally, an instance-level pseudo-label evaluation method is introduced to enhance the available information during the weak supervision process. Finally, a bag-level classifier is used to obtain preliminary WSI classification results. To achieve even more accurate WSI label predictions, we have designed a key instance selection module that strengthens the learning of local features for instances. Combining the results from both modules leads to an improvement in WSI prediction accuracy. ResultsExperiments conducted on Camelyon16, TCGA-NSCLC, SICAPv2, PANDA and classical MIL benchmark datasets demonstrate that our proposed method achieves a competitive performance compared to some recent methods, with maximum improvement of 14.6 % in terms of classification accuracy. ConclusionOur method can improve the classification accuracy of whole slide images in a weakly supervised way, and more accurately detect lesion areas.

Developing a deep learning algorithm to support decision making for the classification of microsatellite instability (MSI) in cancer, using artificial intelligence(AI).

11152 Background: Digital pathology (DP) is an image-based environment, which allows the acquisition, and interpretation of pathological information from a digitized slide. The objective of this work was to build an AI model for predicting MSI in endometrial, colorectal, and gastric carcinomas, to simplify laboratory processes, in a developing country. Nowadays, it is crucial to recognize patients who will respond to treatments such as immunotherapy. Methods: The computational tool utilized was CLAM (clustering-constrained-attention multiple instance learning). This architecture developed by Lu et al. is a deep learning method that utilizes weak supervision and attention based learning, to identify the most relevant regions for tumor classification, in whole slide images (WSI). CLAM was designed to excel in tumor subtyping tasks which are discernible to human visual perception. We are challenging this architecture by employing it in the detection of a molecular phenomenon. For training and internal evaluation, images from TCGA and CPTAC were obtained for endometrial cancer (EC). For colorectal (CCR) and gastric cancer (GC), only images from TCGA. Archived histological samples with MSI/MMR status from a donor lab , were used for external validation. Results: Tests conducted on an internal cohort of 58 samples for CCR and GC revealed a sensitivity of 76.9%, a specificity of 78.1%, and an AUC-ROC of 76.3%. In the case of EC, where 38 cases were evaluated, the sensitivity was 100%, specificity was 68%, and AUC-ROC reached 92%. Notably, regarding the externalcohort consisting of 109 samples, both models demonstrated a high sensitivity of up to 90% in recognizing positive cases. Due to the models’ specificity (approximately 45%), it was not possible to accurately predict MSS samples in all three types of tumors. Conclusions: Promising results were obtained for the first approach in detecting molecular biology events, such as MSI, using AI. CLAM is a useful platform for digital pathology, but new validations are needed to enhance our work and strengthen the model. It is hypothesized that CLAM may not be the best tool for AI in identifying molecular biology events, so other directions are being explored. For external cohorts, preanalytical changes play an important role in obtaining accurate results with scanners and digitalization. It is crucial to teach healthcare professionals about AI in order to ensure its availability, in every diagnostic laboratory.

Zero‐shot insect detection via weak language supervision

AbstractCheap and ubiquitous sensing has made collecting large agricultural datasets relatively straightforward. These large datasets (for instance, citizen science data curation platforms like iNaturalist) can pave the way for developing powerful artificial intelligence (AI) models for detection and counting. However, traditional supervised learning methods require labeled data, and manual annotation of these raw datasets with useful labels (such as bounding boxes or segmentation masks) can be extremely laborious, expensive, and error‐prone. In this paper, we demonstrate the power of zero‐shot computer vision methods—a new family of approaches that require (almost) no manual supervision—for plant phenomics applications. Focusing on insect detection as the primary use case, we show that our models enable highly accurate detection of insects in a variety of challenging imaging environments. Our technical contributions are two‐fold: (a) We curate the Insecta rank class of iNaturalist to form a new benchmark dataset of approximately 6 million images consisting of 2526 agriculturally and ecologically important species, including pests and beneficial insects. (b) Using a vision‐language object detection method coupled with weak language supervision, we are able to automatically annotate images in this dataset with bounding box information localizing the insect within each image. Our method succeeds in detecting diverse insect species present in a wide variety of backgrounds, producing high‐quality bounding boxes in a zero‐shot manner with no additional training cost. This open dataset can serve as a use‐inspired benchmark for the AI community. We demonstrate that our method can also be used for other applications in plant phenomics, such as fruit detection in images of strawberry and apple trees. Overall, our framework highlights the promise of zero‐shot approaches to make high‐throughput plant phenotyping more affordable.