The paper investigates how class imbalance and label shift—common in machine vision due to abundant defect‑free images and limited storage—affect active learning for binary semantic segmentation. It introduces a reproducible simulation protocol that independently varies these two imbalance factors using two open‑source datasets. Four active‑learning strategies (random, entropy‑based, core‑set, and galaxy sampling) are compared, showing that entropy‑based and core‑set methods generally outperform random sampling even under severe imbalance, while quantifying efficiency loss under strong label shift.
arXiv:2606. 07630v1 Announce Type: cross Abstract: Real-world datasets across image and text domains are often characterized by skewed class distributions and noisy annotations, which jointly degrade model performance, particularly on minority classes.
arXiv:2512.12870v2 Announce Type: replace-cross Abstract: Active Learning (AL) is commonly used in applications where labeling data is expensive or time-consuming. In practice, however, labels are of...
arXiv:2505. 03509v3 Announce Type: replace Abstract: Anomaly detection in large datasets is essential in astronomy and computer vision.
arXiv:2510.09877v4 Announce Type: replace-cross Abstract: Over the past couple of decades, many active learning acquisition functions have been proposed, leaving practitioners with an unclear choice...
arXiv:2608. 03511v1 Announce Type: cross Abstract: Active learning (AL) promises to reduce the cost of medical imaging projects by lowering the number of clinical labels required.
The paper introduces a new active learning signal for object detection that relies on a supervised contrastive term added to the training objective. This term shapes an embedding space where distance reflects class membership, allowing an unlabeled detection to be scored by its distance from the predicted category’s region weighted by confidence—all from a single forward pass of one network. Experiments on PASCAL VOC and MS‑COCO show that this criterion outperforms the standard posterior and remains competitive with ensemble‑based methods while incurring only a modest 8.3% increase in parameters.
The paper introduces MOVAL, a model evaluation tool that estimates performance of deep neural networks on unlabeled test data by calibrating class-wise confidence scores. MOVAL mitigates issues from distributional shifts and class imbalance, enabling estimation of metrics beyond accuracy such as F1-Score and AUC. Experiments on natural and medical image datasets demonstrate state‑of‑the‑art results across classification and segmentation tasks, providing accurate class, instance, and pixel‑level performance estimates for safe deployment.
arXiv:2608.28923v1 Announce Type: cross Abstract: Data augmentation is a cornerstone of deep learning pipelines, yet existing strategies treat it as a static, model-agnostic preprocessing step, eithe...
arXiv:2509. 07605v2 Announce Type: replace-cross Abstract: Class imbalance poses a significant challenge to supervised classification, particularly in critical domains like medical diagnostics and anomaly detection where minority class instances are rare.
The paper introduces ActiveKD, a framework that combines active learning with knowledge distillation by using large vision‑language models as teachers. It leverages the structured prediction bias of these models to design Probabilistic CoreSet (PCoreSet), a selection strategy that maximizes coverage in probability space rather than feature space. Experiments on 11 datasets show that ActiveKD improves all selection methods over a no‑distillation baseline, and PCoreSet consistently outperforms random sampling across multiple students and teachers.
arXiv:2606. 08718v1 Announce Type: cross Abstract: While Deep Active Learning (DAL) effectively reduces human annotation costs, its efficacy is constrained by human annotation errors.
arXiv:2610.07698v1 Announce Type: new Abstract: Accurate building footprint extraction from high-resolution remote sensing imagery is essential for urban planning, disaster response, and environmenta...