arXiv Computer Vision October 22, 2026 By Julien Combes (SVH, Michelin), Jean-Fran\c{c}ois Coeurjolly (SVH), Alexandre Derville (Michelin)

Active Learning under Simulated Class Imbalance and Label Shift in Binary Semantic Segmentation

Read the original on arXiv Computer Vision →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

computer-vision

arXiv AI

Jun 9

Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance

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.

By Jiancheng Zhang, Meiqing Li, Qi Zhang, Yinglun Zhu

arXiv AI

Oct 1

Active Learning with Imperfect Labels: Optimal Labeler Assignment and Sample Selection

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...

By Pouya Ahadi, Blair Winograd, Camille Zaug, Karunesh Arora, Lijun Wang, Kamran Paynabar

benchmarks

arXiv Machine Learning

Jun 17

AnomalyMatch: Discovering Rare Objects of Interest with Semi-supervised and Active Learning

arXiv:2505. 03509v3 Announce Type: replace Abstract: Anomaly detection in large datasets is essential in astronomy and computer vision.

By Pablo G\'omez, Laslo E. Ruhberg, Maria Teresa Nardone, David O'Ryan

computer-vision benchmarks

arXiv AI

Oct 15

Batch Bayesian Active Learning with Partial Batch Label Sampling

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...

By Kangping Hu, Stephen Mussmann

rag

arXiv AI

Aug 5

How Many Labels Are Enough? ALDA: Active Learning Deployment Advisor for Medical Image Classification

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.

By Julia Machnio, Mads Nielsen, Mostafa Mehdipour Ghazi

computer-vision

arXiv Computer Vision

Sep 18

Distance to Class Prototypes: Active Learning for Object Detection

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.

By Licheng Zhang, Zheng Gong

rag computer-vision

One email a morning, machine-written

Related stories

Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance

Active Learning with Imperfect Labels: Optimal Labeler Assignment and Sample Selection

AnomalyMatch: Discovering Rare Objects of Interest with Semi-supervised and Active Learning

Batch Bayesian Active Learning with Partial Batch Label Sampling

How Many Labels Are Enough? ALDA: Active Learning Deployment Advisor for Medical Image Classification

Distance to Class Prototypes: Active Learning for Object Detection