The paper compares five machine unlearning (MU) methods—NegGrad, Fine‑Tuning (FT), Random Labeling (RL), SalUn, and MUNBa—on noisy‑label correction across CIFAR‑10, CIFAR‑100, and Food‑101N. Results show that the best MU strategy depends on the noise type: FT works well for most closed‑set noise, RL and SalUn are robust and nearly match retraining accuracy under instance‑dependent noise, while MUNBa excels only under extreme symmetric noise. In open‑set noise, retraining on the cleaned data actually hurts performance, indicating that approximating retraining is not suitable in that regime, yet all MU methods still achieve near‑retraining accuracy on Food‑101N with much lower runtime.
By Jo\~ao L. P. Santana, Filipe R. Cordeiro
arXiv:2606. 11699v1 Announce Type: new Abstract: The performance of machine learning and deep learning models largely depends on the quality of the training data.
By Ha-Linh Nguyen, Hong-Anh Nguyen, Minh-Duc La, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo
The paper proposes a method that first pre‑trains a feature extractor on the target dataset using in‑domain self‑supervised learning (SSL) without labels, then performs standard supervised training on the same noisy dataset. This two‑stage approach eliminates the need for a clean label subset and consistently improves classification accuracy and label‑error detection across synthetic and real‑world noise, especially as noise rates increase. Experiments show that the method matches or surpasses ImageNet and DinoV2 pre‑training, particularly under high noise conditions.
By David Szczecina, Nicholas Pellegrino, Paul Fieguth
arXiv:2607. 23865v1 Announce Type: new Abstract: Supervised deep learning models rely on large, accurately labeled datasets, yet noisy annotations are often unavoidable and can severely degrade performance under high noise levels.
By Chengqi Li, Yangdi Lu, Zhihao Shi, Wenbo He, Chamseddine Talhi, Nadjia Kara
The paper demonstrates that object detection benchmarks suffer from incomplete annotations, with re-annotation of COCO, Pascal VOC, Cityscapes, and KITTI revealing up to a 60% increase in detected objects, especially small, occluded, or densely packed instances. The authors propose a scalable annotation pipeline that uses multiple annotators per object to capture uncertainty and improve recall, and they introduce two new large-scale benchmarks: an uncertainty-aware detection benchmark and a label error detection benchmark based on real errors. Their findings show that benchmark performance is highly sensitive to annotation quality, yet model rankings remain largely unchanged, highlighting the need for uncertainty-aware evaluation to better reflect real-world ambiguity.
By Sarina Penquitt, Jonathan Klees, Antonia van Betteray, Parssa Jashnieh, Peter Stehr, Matthias Rottmann, Lars Schmarje
arXiv:2606. 28654v1 Announce Type: cross Abstract: Deep Neural Network (DNN) classifiers suffer from poor calibration when their softmax outputs (predictive confidence) deviate from the empirical likelihoods.
By Thiru Thillai Nadarasar Bahavan, Sachith Seneviratne, Saman Halgamuge
arXiv:2606. 14965v1 Announce Type: new Abstract: Synthetic instance-dependent label noise (IDN) benchmarks are widely used to evaluate noisy-label learning methods, yet existing approaches typically generate noise through imperfect annotators or classifier raters, leaving the source of ambiguity implicit.
By Shadman Islam, Agustinus Kristiadi, Mostafa Milani
arXiv:2607. 16231v1 Announce Type: new Abstract: Modern neural networks can fit corrupted training labels, making noisy-label learning a useful setting for studying memorization-driven overfitting.
By Richard Mai
arXiv:2607. 05393v1 Announce Type: cross Abstract: Time-domain surveys generate many transient candidates, making Real-Bogus classification a critical step in automated discovery pipelines.
By Rapha\"el Bonnet-Guerrini, Bruno Sanchez, Dominique Fouchez, Benjamin Racine, Maya Guy, Mariam Sabalbal, Manal Yassine, Vincenzo Piuri
arXiv:2608. 04147v1 Announce Type: cross Abstract: Label noise is common in medical imaging datasets due to factors such as inter-rater variability, annotation errors, and ambiguous cases.
By Abhishek Moturu, Babak Taati, Anna Goldenberg
arXiv:2607. 14466v1 Announce Type: new Abstract: Noise injection is a well-known technique in stochastic optimization.
By Matt L. Wiemann, Peter Melchior, Andrew K. Saydjari
arXiv:2510.16211v2 Announce Type: replace
Abstract: Label noise is a common problem in real-world datasets, affecting both model training and validation. Clean data are essential for achieving strong...
By Henrique Pickler, Jorge K. S. Kamassury, Danilo Silva