# Co-learning: Learning from Noisy Labels with Self-supervision Source: [Co-learning: Learning from Noisy Labels with Self-supervision]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:42:15.448Z Authors: Cheng Tan, Jun Xia, Lirong Wu, Stan Z. Li Published: 2021-08-05T06:20:51.000Z ## Abstract Noisy labels, resulting from mistakes in manual labeling or webly data collecting for supervised learning, can cause neural networks to overfit the misleading information and degrade the generalization performance. Self-supervised learning works in the absence of labels and thus eliminates the negative impact of noisy labels. Motivated by co-training with both supervised learning view and self-supervised learning view, we propose a simple yet effective method called Co-learning for learning with noisy labels. Co-learning performs supervised learning and self-supervised learning in a cooperative way. The constraints of intrinsic similarity with the self-supervised module and the structural similarity with the noisily-supervised module are imposed on a shared common feature encoder to regularize the network to maximize the agreement between the two constraints. Co-learning is compared with peer methods on corrupted data from benchmark datasets fairly, and extensive results are provided which demonstrate that Co-learning is superior to many state-of-the-art approaches. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on CIFAR-100 (test) (Instance Accuracy Metrics)](): Image Classification; CIFAR-100 (test); Accuracy (ins-20%): 69.42. - [Image Classification on CIFAR-100 (test) (Asymmetric Noise Robustness)](): Image Classification; CIFAR-100 (test); Test Acc (asym-20%): 65.26. ## Original sources and implementation [Original paper]() [PDF]()