Label noise has been a practical challenge in deep learning due to the strong capability of deep neural networks in fitting all training data.
Learning from the web can ease the extreme dependence of deep learning on large-scale manually labeled datasets.
Due to the memorization effect in Deep Neural Networks (DNNs), training with noisy labels usually results in inferior model performance.
To this end, we propose a certainty-based reusable sample selection and correction approach, termed as CRSSC, for coping with label noise in training deep FG models with web images.
To address this issue, we present an adaptive multi-model framework that resolves polysemy by visual disambiguation.