Ground Truth Labels Research Articles

Masked cross-domain self-supervised deep learning framework for photoacoustic computed tomography reconstruction

Accurate image reconstruction is crucial for photoacoustic (PA) computed tomography (PACT). Recently, deep learning has been used to reconstruct PA images with a supervised scheme, which requires high-quality images as ground truth labels. However, practical implementations encounter inevitable trade-offs between cost and performance due to the expensive nature of employing additional channels for accessing more measurements. Here, we propose a masked cross-domain self-supervised (CDSS) reconstruction strategy to overcome the lack of ground truth labels from limited PA measurements. We implement the self-supervised reconstruction in a model-based form. Simultaneously, we take advantage of self-supervision to enforce the consistency of measurements and images across three partitions of the measured PA data, achieved by randomly masking different channels. Our findings indicate that dynamically masking a substantial proportion of channels, such as 80%, yields meaningful self-supervisors in both the image and signal domains. Consequently, this approach reduces the multiplicity of pseudo solutions and enables efficient image reconstruction using fewer PA measurements, ultimately minimizing reconstruction error. Experimental results on in-vivo PACT dataset of mice demonstrate the potential of our self-supervised framework. Moreover, our method exhibits impressive performance, achieving a structural similarity index (SSIM) of 0.87 in an extreme sparse case utilizing only 13 channels, which outperforms the performance of the supervised scheme with 16 channels (0.77 SSIM). Adding to its advantages, our method can be deployed on different trainable models in an end-to-end manner, further enhancing its versatility and applicability.

Potential and Limitations of Anomaly Detection via Tower-Radar Monitoring of Wind Turbine Blades in Regular Operation with Convolutional Networks

The authors have already presented a first analysis of a field study on radar- based structural health monitoring of rotor blades on two operational wind turbines. This analysis will now be extended with measurements from a third operational wind turbine used as a case study for structural monitoring of individual rotor blades over different time intervals and blade modifications. More precisely, a sensor box with a 35 GHz FMCW radar and a highspeed camera was positioned at 90m height on the turbine tower, collecting radar data for structural information and videos for automatic ground truth labelling. After two months of collecting data, each individual rotor blade of that turbine was differently modified and measured again. The radar-facing surface of one rotor blade was partially coated with a microwave absorber foil, while an equivalent foil was applied to the backside of the second rotor blade. The third rotor blade was intentionally left unchanged for the sake of comparability. This study investigates potential limitations like general dataset complexity in radar-based anomaly detection for operational wind turbines. Furthermore, the discriminative ability of a convolutional neural network for classifying moving rotor blades is discussed when encountering feature drift through changing environmental and operational conditions, i.e. metadata like nacelle orientation, rotor blade pitch and rotation speed.

Ground penetrating radar for moisture assessment in railway tracks: An experimental investigation

The health monitoring of railway networks offers a means to ensuring high-quality service, avoiding safety risks, and optimally planning maintenance actions to minimize life-cycle costs. Monitoring of the substructure is particularly linked to the tracking of degradation, which often stems from water infiltration, causing moisture accumulation in the underlying ballast layers. Such deterioration incurs substantial expenses in the order of several million per annum, while reducing the useful life of the track infrastructure. In optimizing management, it is important to improve detection schemes via affordable and non-invasive procedures. Such a solution is found in use of Ground Penetrating Radar (GPR) technology, which employs non-invasive radar pulses to map the subsurface, and possibly detect water infiltration. Train-based GPR systems thus offer tremendous potential for the development of preventive and automated monitoring of railway network infrastructure. Nevertheless, despite previous efforts in this direction, the technology remains relatively under-explored and lacks comprehensive studies to establish its suitability for this task. Moreover, there is no consensus on a standardized procedure for automatic inference of reliable indicators of railway health from GPR observations. In this work, we report on an extensive experimental analysis conducted on a controlled railway track, built by the Swiss Federal Railways, for this campaign. The humidity condition of the railway track was artificially altered to reach different levels of water content and GPR measurements were gathered under the varying conditions, with ground truth assessed through lab tests on collected samples. GPR data with complete ground truth labels deliver a rare benchmark, which can enhance understanding of this technology. Our findings show that GPR systems can effectively detect moisture infiltration in railway tracks, although several challenges are to be addressed for the development of accurate, automated procedures.

Automated algorithm for medical data structuring, and segmentation using artificial intelligence within secured environment for dataset creation

ObjectiveRoutinely collected electronic health records using artificial intelligence (AI)-based systems bring out enormous benefits for patients, healthcare centers, and its industries. Artificial intelligence models can be used to structure a wide variety of unstructured data. MethodsWe present a semi-automatic workflow for medical dataset management, including data structuring, research extraction, AI-ground truth creation, and updates. The algorithm creates directories based on keywords in new file names. ResultsOur work focuses on organizing computed tomography (CT), magnetic resonance (MR) images, patient clinical data, and segmented annotations. In addition, an AI model is used to generate different initial labels that can be edited manually to create ground truth labels. The manually verified ground truth labels are later included in the structured dataset using an automated algorithm for future research. ConclusionThis is a workflow with an AI model trained on local hospital medical data with output based/adapted to the users and their preferences. The automated algorithms and AI model could be implemented inside a secondary secure environment in the hospital to produce inferences.

Few-shot online anomaly detection and segmentation

Detecting anomaly patterns from images is a crucial artificial intelligence technique in industrial applications. Recent research in this domain has emphasized the necessity of a large volume of training data, overlooking the practical scenario where, post-deployment of the model, unlabeled data containing both normal and abnormal samples can be utilized to enhance the performance. Consequently, this paper focuses on addressing the challenging yet practical few-shot online anomaly detection and segmentation (FOADS) task. Under the FOADS framework, models are trained on a few-shot normal dataset, followed by inspection and improvement of their capabilities by leveraging unlabeled streaming data containing both normal and abnormal samples simultaneously. Since the data stream has no ground truth labels, the model needs to filter the anomalous data by detection to avoid contaminating its parameters, which presents a significant challenge when initial samples are insufficient. To tackle this issue, we propose modeling the feature distribution of normal images using a Neural Gas network, which offers the flexibility to adapt the topology structure to identify outliers in the data flow. In order to achieve improved performance with limited training samples, we employ multi-scale feature embedding extracted from a CNN pre-trained on ImageNet to obtain a robust representation. Furthermore, we introduce an algorithm that can incrementally update parameters without the need to store previous samples. Comprehensive experimental results demonstrate that our method can achieve substantial performance under the FOADS setting, while ensuring that the time complexity remains within an acceptable range on MVTec AD and BTAD datasets.

Moving toward Automaticity: A Robust Synthetic Occlusion Image Method for High-Throughput Mushroom Cap Phenotype Extraction

Mushroom cap is a key trait in the growth process and its phenotypic parameters are essential for automatic cultivation and smart breeding. However, the edible mushrooms are usually grown densely with mutual occlusion, which is difficult to obtain the phenotypic parameters non-destructively. Although deep learning methods achieve impressive performance with superior generalization capabilities, they require a large amount of ground truth label of the occluded target, which is a challenging task due to the substantial workload. To overcome this obstacle, a novel synthetic cap occlusion image method was proposed for rapidly generating edible mushroom occlusion datasets using raw images, in which the ground truth is obtained from the real world and the occlusion is randomly generated for simulating real scenes. Moreover, variants of amodal instance segmentation models with different backbone were trained and evaluated on our synthetic occlusion image datasets. Finally, an amodal mask-based size estimation method was presented to calculate the width and length of the cap. The experimental results showed that the amodal instance segmentation achieved an AP@[0.5:0.95] of 82%, 93% and 96% on Oudemansiella raphanipes, Agrocybe cylindraceas and Pholiota nameko synthetic cap datasets, respectively, with a size of 1024 × 1024 px, which indicates that our occlusion image synthesis method can effectively simulate the real cap occlusion situation. The size estimation method achieved an R2 of 0.95 and 0.98 between predictive amodal caps and manually labeled caps for the length and width of Agrocybe cylindraceas cap, respectively, which can be applied to obtain the phenotypic parameters of each cap effectively and accurately. These methods not only meet the demand for automatic monitoring of edible mushroom morphology in factories but also provide technical support for intelligent breeding.

Self-paced method for transfer partial label learning

In partial label learning (PLL) problem, each training sample corresponds to a group of candidate labels, in which only one label is the ground-truth label (correct label). Almost all the existing PLL algorithms attempt to eliminate the ambiguity of the candidate label sets by treating all labels indiscriminately. However, this kind of approach lacks the consideration of the complexity between the labels and the instances in the training process. Encouraged by the extensive researches of the self-paced learning (SPL) and transfer learning (TL) in various fields, this paper introduces SPL and TL together to address the PLL problem and proposes a new SPL framework, which is called self-paced method for transfer partial label learning (SPTPLL). The proposed model utilizes transfer learning model to share the parameters and regularization terms of the Support Vector Machine (SVM), which can transfer knowledge from the source task to the target task. Additionally, we implement the self-paced learning scheme by choosing a suitable self-paced function to enhance the robustness of the proposed model. In the process of learning iteration, the priority of training examples with their candidate labels is ranked through self-paced learning to control the learning process. Finally, we demonstrate the superior performance of the proposed method through a large number of experiments compared with state-of-the-art baseline methods.

Onward and Autonomously: Expanding the Horizon of Image Segmentation for Self-Driving Cars through Machine Learning

Autonomous navigation is the leading technology in current era, in this intelligent traffic light, sign detection, ADAS and obstacle detections were playing major role. Image segmentation is the process of dividing an image into different regions, or semantic classes. This is a challenging problem in autonomous vehicle technology because it requires the vehicle to be able to understand its surroundings to safely navigate. The major challenges in this platform are the accuracy and efficiency of model performance. The proposed method in the abstract uses a convolutional neural network (CNN) to perform image segmentation. CNNs are a type of deep learning model that is well-suited for image processing tasks. The CNN in this paper was trained on a local city dataset, and it was able to achieve a mean intersection over union (IoU) of 73%. IoU is a measure of how well the segmentation results match the ground truth labels. A score of 100% indicates that the segmentation is perfect, while a score of 0% indicates that the segmentation is completely wrong. This means that the method can segment images at a very fast rate, which is important for autonomous vehicles that need to make real-time decisions. Overall, the proposed method is a promising approach for image segmentation in autonomous vehicles. It can achieve high accuracy and speed, and it is easy to implement using Python. The proposed method attains an accuracy of 98.34 %, a Sensitivity of 97.26 % and a sensitivity of 96.37 % had been attained. The method could be used to improve the safety and efficiency of autonomous vehicles by enabling them to better understand their surroundings.

Enhancing learning on uncertain pixels in self-distillation for object segmentation

Self-distillation method guides the model learning via transferring knowledge of the model itself, which has shown the advantages in object segmentation. However, it has been proved that uncertain pixels with predicted probability close to 0.5 will restrict the model performance. The existing self-distillation methods cannot guide the model to enhance its learning ability for uncertain pixels, so the improvement is limited. To boost the student model’s learning ability for uncertain pixels, a novel self-distillation method is proposed. Firstly, the predicted probability in the current training sample and the ground truth label are fused to construct the teacher knowledge, as the current predicted information can express the performance of student models and represent the uncertainty of pixels more accurately. Secondly, a quadratic mapping function between the predicted probabilities of the teacher and student model is proposed. Theoretical analysis shows that the proposed method using the mapping function can guide the model to enhance the learning ability for uncertain pixels. Finally, the essential difference of utilizing the predicted probability of the student model in self-distillation is discussed in detail. Extensive experiments were conducted on models with convolutional neural networks and Transformer architectures as the backbone networks. The results on four public datasets demonstrate that the proposed method can effectively improve the student model performance.

Noise4Denoise: Leveraging noise for unsupervised point cloud denoising

Existing deep learning-based point cloud denoising methods are generally trained in a supervised manner that requires clean data as ground-truth labels. However, in practice, it is not always feasible to obtain clean point clouds. In this paper, we introduce a novel unsupervised point cloud denoising method that eliminates the need to use clean point clouds as groundtruth labels during training. We demonstrate that it is feasible for neural networks to only take noisy point clouds as input, and learn to approximate and restore their clean versions. In particular, we generate two noise levels for the original point clouds, requiring the second noise level to be twice the amount of the first noise level. With this, we can deduce the relationship between the displacement information that recovers the clean surfaces across the two levels of noise, and thus learn the displacement of each noisy point in order to recover the corresponding clean point. Comprehensive experiments demonstrate that our method achieves outstanding denoising results across various datasets with synthetic and real-world noise, obtaining better performance than previous unsupervised methods and competitive performance to current supervised methods.

Exploiting indirect linear correlation for label distribution learning

Label distribution learning represents the relevance of labels to samples using description degree, which can provide richer semantic information, thus finding wider applications. Exploiting label correlations is an effective approach to narrow down the hypothesis space of label distribution learning models. In existing works that utilize low-rank assumptions or label linear dependence to mine correlations, it is assumed that a label can be linearly expressed by other labels. However, this assumption can only be satisfied when there are linear dependency relationships between labels, thus the label correlation obtained by such methods is subject to certain distortion. To address this issue, this paper assumes that labels can be linearly represented by the same set of bases. The correlation between labels is represented by sharing common bases. Specifically, the paper employs matrix factorization to extract bases that can be used to represent all labels. And then designs a label distribution learning algorithm based on the property of sharing the same set of bases of the ground truth label distribution and predict label distribution. The effectiveness of the algorithm is verified through experimental validation. Generally speaking, the algorithm presented in this paper achieves optimal performance at 73.15% of the cases, with the best average ranking. In the two-tailed t-test, the algorithm in this paper exhibits statistical superiority compared to all comparison algorithms.

GBVSSL: Contrastive Semi-Supervised Learning Based on Generalized Bias-Variance Decomposition

Mainstream semi-supervised learning (SSL) techniques, such as pseudo-labeling and contrastive learning, exhibit strong generalization abilities but lack theoretical understanding. Furthermore, pseudo-labeling lacks the label enhancement from high-quality neighbors, while contrastive learning ignores the supervisory guidance provided by genuine labels. To this end, we first introduce a generalized bias-variance decomposition framework to investigate them. Then, this research inspires us to propose two new techniques to refine them: neighbor-enhanced pseudo-labeling, which enhances confidence-based pseudo-labels by incorporating aggregated predictions from high-quality neighbors; label-enhanced contrastive learning, which enhances feature representation by combining enhanced pseudo-labels and ground-truth labels to construct a reliable and complete symmetric adjacency graph. Finally, we combine these two new techniques to develop an excellent SSL method called GBVSSL. GBVSSL significantly surpasses previous state-of-the-art SSL approaches in standard benchmarks, such as CIFAR-10/100, SVHN, and STL-10. On CIFAR-100 with 400, 2500, and 10,000 labeled samples, GBVSSL outperforms FlexMatch by 3.46%, 2.72%, and 2.89%, respectively. On the real-world dataset Semi-iNat 2021, GBVSSL improves the Top-1 accuracy over CCSSL by 4.38%. Moreover, GBVSSL exhibits faster convergence and enhances unbalanced SSL. Extensive ablation and qualitative studies demonstrate the effectiveness and impact of each component of GBVSSL.

Deep learning automatic semantic segmentation of glioblastoma multiforme regions on multimodal magnetic resonance images.

In patients having naïve glioblastoma multiforme (GBM), this study aims to assess the efficacy of Deep Learning algorithms in automating the segmentation of brain magnetic resonance (MR) images to accurately determine 3D masks for 4 distinct regions: enhanced tumor, peritumoral edema, non-enhanced/necrotic tumor, and total tumor. A 3D U-Net neural network algorithm was developed for semantic segmentation of GBM. The training dataset was manually delineated by a group of expert neuroradiologists on MR images from the Brain Tumor Segmentation Challenge 2021 (BraTS2021) image repository, as ground truth labels for diverse glioma (GBM and low-grade glioma) subregions across four MR sequences (T1w, T1w-contrast enhanced, T2w, and FLAIR) in 1251 patients. The in-house test was performed on 50GBM patients from our cohort (PerProGlio project). By exploring various hyperparameters, the network's performance was optimized, and the most optimal parameter configuration was identified. The assessment of the optimized network's performance utilized Dice scores, precision, and sensitivity metrics. Our adaptation of the 3D U-net with additional residual blocks demonstrated reliable performance on both the BraTS2021 dataset and the in-house PerProGlio cohort, employing only T1w-ce sequences for enhancement and non-enhanced/necrotic tumor models and T1w-ce + T2w + FLAIR for peritumoral edema and total tumor. The mean Dice scores (training and test) were 0.89 and 0.75; 0.75 and 0.64; 0.79 and 0.71; and 0.60 and 0.55, for total tumor, edema, enhanced tumor, and non-enhanced/necrotic tumor, respectively. The results underscore the high precision with which our network can effectively segment GBM tumors and their distinct subregions. The level of accuracy achieved agrees with the coefficients recorded in previous GBM studies. In particular, our approach allows model specialization for each of the different tumor subregions employing only those MR sequences that provide value for segmentation.

Utilizing convolutional neural networks for discriminating cancer and stromal cells in three-dimensional cell culture images with nuclei counterstain.

Accurate cell segmentation and classification in three-dimensional (3D) images are vital for studying live cell behavior and drug responses in 3D tissue culture. Evaluating diverse cell populations in 3D cell culture over time necessitates non-toxic staining methods, as specific fluorescent tags may not be suitable, and immunofluorescence staining can be cytotoxic for prolonged live cell cultures. We aim to perform machine learning-based cell classification within a live heterogeneous cell culture population grown in a 3D tissue culture relying only on reflectance, transmittance, and nuclei counterstained images obtained by confocal microscopy. In this study, we employed a supervised convolutional neural network (CNN) to classify tumor cells and fibroblasts within 3D-grown spheroids. These cells are first segmented using the marker-controlled watershed image processing method. Training data included nuclei counterstaining, reflectance, and transmitted light images, with stained fibroblast and tumor cells as ground-truth labels. Our results demonstrate the successful marker-controlled watershed segmentation of 84% of spheroid cells into single cells. We achieved a median accuracy of 67% (95% confidence interval of the median is 65-71%) in identifying cell types. We also recapitulate the original 3D images using the CNN-classified cells to visualize the original 3D-stained image's cell distribution. This study introduces a non-invasive toxicity-free approach to 3D cell culture evaluation, combining machine learning with confocal microscopy, opening avenues for advanced cell studies.

Use of an AI-powered visualization platform to support precision clinical decision-making in patients with breast cancer undergoing neoadjuvant chemotherapy.

e12618 Background: Chemotherapy to reduce cancer burden and tumor size ("downstaging") is widely used in neoadjuvant treatment of early-stage breast cancer (ESBC) and can have a dramatic impact on selection of further treatment courses, including surgery. The resulting decision-making process between physicians and cancer patients requires detailed and effective communication of the patient's disease status, and clear presentation of this information in Tumor Board settings. Artificial intelligence (AI) -powered visualization platforms offer the potential to aid in evaluating breast tumor location and morphology, and accordingly optimize treatment. Additionally, these tools offer enhanced communication with patients regarding future treatment options, particularly serving as clinical decision support (CDS) tools. Methods: We assessed the performance of an AI platform that employs dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to render three-dimensional (3D) visualizations of breast tumors and 5 additional chest tissues on an independent validation dataset comprise of 100 ESBC cases with ground-truth tumor labels vetted by 2 breast-specialized radiologists. The platform provides 3D depictions of the tumor and its multi-tissue context, as well as functionalities for quantifying tumor morphology, tumor-to-landmark structure distances, excision volumes, and approximate surgical margins. We subsequently evaluated the tool's utility in a real-world setting to understand how the tool impacts clinical decision-making and patient communication, specifically around surgical planning in the context of neoadjuvant chemotherapy (NACT). Results: The platform generated accurate 3D tumor maps, as evidenced by a median Dice score of 75.6% and a median Hausdorff distances of 15.1 mm relative to the radiologist validation set. The automatic longest tumor dimension calculations were linearly correlated with radiologist direct measurements (Pearson correlation coefficient = 0.78) and had a median absolute difference of 6.3 mm. We found strong overlap between the platform’s ground-truth convex hulls, as shown by a median Dice score of 81.5%. When used by a skilled breast-specialized surgeon, the tool enabled rapid and intuitive patient-physician communication of the location and extent of disease, and potential degrees of downstaging to breast-conserving surgery. Conclusions: Detailed 3D tumor and surrounding multi-tissue depictions offer both qualitative and quantitative comprehension of cancer topology and may aid in formulating an optimal treatment approach for breast cancer treatment. We show that detailed depictions enhance communication between physicians and patients and may aid in streamlining decision-making.

Automatic Ground-Truth Image Labeling for Deep Neural Network Training and Evaluation Using Industrial Robotics and Motion Capture

Abstract The United States Navy (USN) intends to increase the amount of uncrewed aircraft in a carrier air wing. To support this increase, carrier-based uncrewed aircraft will be required to have some level of autonomy as there will be situations where a human cannot be in/on the loop. However, there is no existing and approved method to certify autonomy within Naval Aviation. In support of generating certification evidence for autonomy, the United States Naval Academy (USNA) has created a training and evaluation system (TES) to provide quantifiable metrics for feedback performance in autonomous systems. The preliminary use case for this work focuses on autonomous aerial refueling. Prior demonstrations of autonomous aerial refueling have leveraged a deep neural network (DNN) for processing visual feedback to approximate the relative position of an aerial refueling drogue. The training and evaluation system proposed in this work simulates the relative motion between the aerial refueling drogue and feedback camera system using industrial robotics. Ground-truth measurements of the pose between the camera and drogue are measured using a commercial motion capture system. Preliminary results demonstrate calibration methods providing ground-truth measurements with millimeter precision. Leveraging this calibration, the proposed system is capable of providing large-scale datasets for DNN training and evaluation against a precise ground truth.

Local dominance unveils clusters in networks

Clusters or communities can provide a coarse-grained description of complex systems at multiple scales, but their detection remains challenging in practice. Community detection methods often define communities as dense subgraphs, or subgraphs with few connections in-between, via concepts such as the cut, conductance, or modularity. Here we consider another perspective built on the notion of local dominance, where low-degree nodes are assigned to the basin of influence of high-degree nodes, and design an efficient algorithm based on local information. Local dominance gives rises to community centers, and uncovers local hierarchies in the network. Community centers have a larger degree than their neighbors and are sufficiently distant from other centers. The strength of our framework is demonstrated on synthesized and empirical networks with ground-truth community labels. The notion of local dominance and the associated asymmetric relations between nodes are not restricted to community detection, and can be utilised in clustering problems, as we illustrate on networks derived from vector data.

Evaluating Sex-specific Differences in Abdominal Fat Volume and Proton Density Fat Fraction at MRI Using Automated nnU-Net-based Segmentation.

Sex-specific abdominal organ volume and proton density fat fraction (PDFF) in people with obesity during a weight loss intervention was assessed with automated multiorgan segmentation of quantitative water-fat MRI. An nnU-Net architecture was employed for automatic segmentation of abdominal organs, including visceral and subcutaneous adipose tissue, liver, and psoas and erector spinae muscle, based on quantitative chemical shift-encoded MRI and using ground truth labels generated from participants of the Lifestyle Intervention (LION) study. Each organ's volume and fat content were examined in 127 participants (73 female and 54 male participants; body mass index, 30-39.9 kg/m2) and in 81 (54 female and 32 male participants) of these participants after an 8-week formula-based low-calorie diet. Dice scores ranging from 0.91 to 0.97 were achieved for the automatic segmentation. PDFF was found to be lower in visceral adipose tissue compared with subcutaneous adipose tissue in both male and female participants. Before intervention, female participants exhibited higher PDFF in subcutaneous adipose tissue (90.6% vs 89.7%; P < .001) and lower PDFF in liver (8.6% vs 13.3%; P < .001) and visceral adipose tissue (76.4% vs 81.3%; P < .001) compared with male participants. This relation persisted after intervention. As a response to caloric restriction, male participants lost significantly more visceral adipose tissue volume (1.76 L vs 0.91 L; P < .001) and showed a higher decrease in subcutaneous adipose tissue PDFF (2.7% vs 1.5%; P < .001) than female participants. Automated body composition analysis on quantitative water-fat MRI data provides new insights for understanding sex-specific metabolic response to caloric restriction and weight loss in people with obesity. Keywords: Obesity, Chemical Shift-encoded MRI, Abdominal Fat Volume, Proton Density Fat Fraction, nnU-Net ClinicalTrials.gov registration no. NCT04023942 Supplemental material is available for this article. Published under a CC BY 4.0 license.

Enhanced Attention Guided Teacher–Student Network for Weakly Supervised Object Detection

Weakly Supervised Object Detection (WSOD) has attracted increasing attention due to the convenience and low-cost of acquiring image-level annotations. Most existing WSOD methods follow Multiple Instance Learning (MIL) paradigm to select bounding boxes from proposals based on their classification scores. However, MIL-based WSOD methods often focus on discriminative regions, leading to incomplete and missing instances. To address these issues, we introduce a novel WSOD framework named Enhanced Attention Guided Teacher–Student Network (EATSN). This framework aims to improve detection performance through the guidance of attention map and consistency learning. specifically, we initially train a teacher network using MIL process to generate pseudo ground-truth labels. Subsequently, the weak augmented and strong augmented images are fed into teacher and student models to produce the enhanced attention map. During the training iterations, pseudo labels are utilized to guide the student model, while the teacher model refines its parameters through the Exponential Moving Average(EMA) from the student. Finally we design a proposal selection method that leverages the enhanced attention map and bounding boxes scores to achieve better detection results. Experimental results on benchmark datasets demonstrate that our method achieves comparable performance.

Crowdsourcing with the drift diffusion model of decision making.

Crowdsourcing involves the use of annotated labels with unknown reliability to estimate ground truth labels in datasets. A common task in crowdsourcing involves estimating reliabilities of annotators (such as through the sensitivities and specificities of annotators in the binary label setting). In the literature, beta or dirichlet distributions are typically imposed as priors on annotator reliability. In this study, we investigated the use of a neuroscientifically validated model of decision making, known as the drift-diffusion model, as a prior on the annotator labeling process. Two experiments were conducted on synthetically generated data with non-linear (sinusoidal) decision boundaries. Variational inference was used to predict ground truth labels and annotator related parameters. Our method performed similarly to a state-of-the-art technique (SVGPCR) in prediction of crowdsourced data labels and prediction through a crowdsourced-generated Gaussian process classifier. By relying on a neuroscientifically validated model of decision making to model annotator behavior, our technique opens the avenue of predicting neuroscientific biomarkers of annotators, expanding the scope of what may be learnt about annotators in crowdsourcing tasks.