# EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labels Source: [EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labels]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:43:58.904Z Authors: Ragav Sachdeva, Filipe R. Cordeiro, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro Published: 2020-11-11T11:15:32.000Z ## Abstract The efficacy of deep learning depends on large-scale data sets that have been carefully curated with reliable data acquisition and annotation processes. However, acquiring such large-scale data sets with precise annotations is very expensive and time-consuming, and the cheap alternatives often yield data sets that have noisy labels. The field has addressed this problem by focusing on training models under two types of label noise: 1) closed-set noise, where some training samples are incorrectly annotated to a training label other than their known true class; and 2) open-set noise, where the training set includes samples that possess a true class that is (strictly) not contained in the set of known training labels. In this work, we study a new variant of the noisy label problem that combines the open-set and closed-set noisy labels, and introduce a benchmark evaluation to assess the performance of training algorithms under this setup. We argue that such problem is more general and better reflects the noisy label scenarios in practice. Furthermore, we propose a novel algorithm, called EvidentialMix, that addresses this problem and compare its performance with the state-of-the-art methods for both closed-set and open-set noise on the proposed benchmark. Our results show that our method produces superior classification results and better feature representations than previous state-of-the-art methods. The code is available at https://github.com/ragavsachdeva/EvidentialMix. ## 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 CIFAR10 Noise ratio 0.3, Open ratio 0.5 (test)](): Image Classification; CIFAR10 Noise ratio 0.3, Open ratio 0.5 (test); Best Accuracy: 94.5. - [Image Classification on CIFAR10 Noise ratio 0.3, Open ratio 1.0 (test)](): Image Classification; CIFAR10 Noise ratio 0.3, Open ratio 1.0 (test); Best Accuracy: 0.929. - [Image Classification on CIFAR10 Noise ratio 0.6, Open ratio 0.5 (test)](): Image Classification; CIFAR10 Noise ratio 0.6, Open ratio 0.5 (test); Best Accuracy: 93.4. - [Image Classification on CIFAR10 Noise ratio 0.6, Open ratio 1.0 (test)](): Image Classification; CIFAR10 Noise ratio 0.6, Open ratio 1.0 (test); Accuracy: 90.6. ## Original sources and implementation [Original paper]() [PDF]()