A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Curtis G. Northcutt, Lu Jiang, Isaac L. Chuang
Confident learning estimates uncertainty in dataset labels by identifying label errors using a class-conditional noise model, outperforming seven methods on CIFAR and improving model accuracy.
Olatomiwa O. Bifarin
Tree-based SHAP provides deeper interpretability than PLS-DA VIP scores for explaining machine learning models in metabolomics binary classification.
Zhengxia Zou, Keyan Chen, Zhenwei Shi, et al.
A comprehensive survey tracing 25 years of object detection evolution, from 1990s hand-crafted methods to modern deep learning detectors, covering milestones, datasets, metrics, and architectures.
Olivier Bernard, Alain Lalande, Clément Zotti, et al.
Introduces the ACDC dataset and benchmarks deep learning methods for automatic cardiac MRI segmentation and diagnosis, achieving near-expert accuracy.
Catherine Wah
CUB-200-2011 extends the CUB-200 dataset to 200 bird species with doubled images per category, new part localization annotations, and benchmarks for categorization and part localization.
Bo Li, Yuanhan Zhang, Liangyu Chen, et al.
Otter is a multi-modal model instruction-tuned with both textual and visual in-context examples, supported by the MIMIC-IT dataset of over 3 million instruction-response pairs.
Shervin Minaee, Yuri Y. Boykov, Fatih Porikli, et al.
A comprehensive survey of deep learning approaches for image segmentation, covering architectures, datasets, performance comparisons, and future directions.
Fuzhen Zhuang, Zhiyuan Qi, Keyu Duan, et al.
A comprehensive survey systematizing transfer learning research, reviewing 40+ approaches and benchmarking 20+ models on three datasets.
Unknown
AutoDEUQ automates deep ensemble construction with uncertainty quantification, evaluated on 10 regression benchmark datasets.
Watchara Ruangsang, Patiyuth Pramkeaw
Cross-dataset evaluation of YOLOv8 for UAV fire and smoke detection reveals benchmark contamination and strong zero-shot transfer.
Unknown
DOVE is a large-scale, multi-dimensional predictions dataset released to enable more meaningful and generalizable evaluation of large language models.
Unknown
The paper analyzes uncertainty calibration of process reward models, extending evaluation to a 72B parameter variant on MATH500 and AIME24-25 datasets.