CORTEXA
← Browse
arxiveess.IVcs.LG2026-07-01

Group-invariant Coresets for Data-efficient Active Learning

L. C. Ayres, J. C. M. Bermudez, S. J. M. de Almeida, R. A. Borsoi

Active learning reduces labeling cost by querying the most informative unlabeled samples, but standard coreset methods ignore known data symmetries and can waste budget on transformed versions of the same instance. We propose GRINCO, a group-invariant coreset framework that performs acquisition in the quotient space induced by a transformation group, so that selection operates on orbits rather than raw samples. The method uses either canonical representatives or learned orbit-separating invariant embeddings to define practical quotient metrics, and combines quotient-space k-center selection with invariant training through an orbit-averaged loss. We further derive a generalization bound that relates excess orbit-averaged risk to quotient-space coverage, label uncertainty, and intra-orbit variability. Experiments on synthetic scale-invariant data and image benchmarks with rotation-induced redundancy show that GRINCO improves orbit coverage and achieves stronger label efficiency than conventional coreset baselines, especially when group-induced redundancy is substantial.

View free PDFSource page

Related papers

arxiveess.IVcs.CVcs.LG2026-07-31

MoPET: Parameter-Efficient Mixture-of-Experts for Unified Medical Image Classification

Sebastian Doerrich, Daniel Würtinger, Francesco Di Salvo, Shyam Nandan Rai, Christian Ledig

Adapting deep learning models to profound clinical heterogeneity typically relies on parameter-efficient fine-tuning (PEFT) to avoid the severe overfitting associated with full end-to-end network updates. Although PEFT successfully navigates limited data scenarios, it inherently…

View free PDFSource page
arxivcs.CVcs.AIcs.LGeess.IV2026-07-23

Synthetic data generation framework for quality control automation in gravure printing

Korota Arsène Coulibaly, Mohamed Hamlich, Khalid Hmali, Andrea Trombin

Quality control in printing, particularly in rotogravure printing, still depends on slow, costly, and subjective manual inspection. Automated surface defect detection is critical for maintaining high-quality standards in rotogravure printing. Deep learning models give prospects f…

View free PDFSource page
arxiveess.IVcs.LG2026-07-31

Few-shot Deep Learning for Phase-Amplitude Aberration Correction in Transcranial Focused Ultrasound

Minju Seol, Minjee Seo, Seonaeng Cho, Kyungho Yoon

Transcranial focused ultrasound (tFUS) is a non-invasive technique that delivers focused acoustic energy through the skull for neuromodulation and therapeutic applications. However, the heterogeneous structure of the skull induces complex, patient-specific phase and amplitude abe…

View free PDFSource page
arxivcs.CVcs.LGeess.IV2026-07-24

Farmland Extent and Visible Boundary Mapping from 1 m NAIP Imagery Using Residual U-Net and Text-Prompted SAM 3 Refinement

Mohammadreza Narimani, Vikram Anand, Parastoo Farajpoor

Agricultural field maps are often proprietary, incomplete, or outdated, yet they provide the spatial framework for crop monitoring, production accounting, and land-conversion analysis. This study presents a reproducible workflow for mapping farmland extent and visible boundaries…

View free PDFSource page
arxivcs.LGcs.DB2026-07-31

Curriculum Matters: Data-Efficient Relational PFN Pretraining with Synthetic Data

Mohammad Sadeq Abolhasani, Viswanath Ganapathy

Relational Prior-Data Fitted Networks (PFNs) such as RDB-PFN approximate Bayesian inference over multi-table relational databases by pretraining on millions of synthetic tasks. We investigate three intertwined questions about this paradigm. First, can a structurally different syn…

View free PDFSource page
arxivcs.LGphysics.comp-ph2026-07-24

Latent PDE mapping for efficient physics-informed learning across geometries with limited data

Ingvild Askim Adde, Mary M. Maleckar, Gabriel Balaban

In this study, we introduce latent PDE mapping, a broadly applicable physics-informed learning technique designed to enable efficient geometric generalization with sparse training data. Latent PDE mapping pulls back geometry-specific PDE residuals and boundary conditions to a pre…

View free PDFSource page