2021/02/01 by Jason Z. Lin, Lin, Jason Z., Jelena Bradić +2 · 3 citations
Computer Science · Mathematics · #Anomaly Detection Techniques and Applications #Artificial intelligence #Artificial neural network #Benchmark (surveying) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Deep learning #FOS: Computer and information sciences #Focus (optics) #Generalization #Imbalanced Data Classification Techniques #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Machine learning #Margin (machine learning) #Mathematics #Memorization #Methodology (stat.ME) #Noise (video) #Pattern recognition (psychology) #cs.CV #cs.LG #stat.ME #stat.ML
paper · pdf · doi:10.48550/arxiv.2102.00751
published in arXiv (Cornell University) (Cornell University) · 23 pages, 9 sets of figures
openalex publication_date 2021/02/01 · arxiv created 2021/09/02 · arxiv updated 2021/09/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
A deep neural network trained on noisy labels is known to quickly lose its power to discriminate clean instances from noisy ones. After the early learning phase has ended, the network memorizes the noisy instances, which leads to a significant degradation in its generalization performance. To resolve this issue, we propose MARVEL (MARgins Via Early Learning), a new robust learning method where the memorization of the noisy instances is curbed. We propose a new test statistic that tracks the goodness of "fit" of every instance based on the epoch-history of its classification margins. If its classification margin is small in a sequence of consecutive learning epochs, that instance is declared noisy and the network abandons learning on it. Consequently, the network first flags a possibly noisy instance, and then waits to see if learning on that instance can be improved and if not, the network learns with confidence that this instance can be safely abandoned. We also propose MARVEL+, where arduous instances can be upweighted, enabling the network to focus and improve its learning on them and consequently its generalization. Experimental results on benchmark datasets with synthetic label noise and real-world datasets show that MARVEL outperforms other baselines consistently across different noise levels, with a significantly larger margin under asymmetric noise.