- An Embedding is Worth a Thousand Noisy Labels

Accuracy (↑) on two clean and noisy datasets (Wei et al., 2022). The two best results are highlighted in bold. Note that NR stands for Noise Rate. CIFAR-10N includes three annotations per image, and Noisy split denotes various aggregation strategies. Following the proposed naming convention, Aggr refers to a majority voting, R-i (i ∈ {1, 2, 3}) denotes the i-th submitted label for each image, and Worst denotes the selection of only wrong labels, if applicable. Conversely, CIFAR-100N presents just one annotation per image, thereby offering one single noisy split.

Go to figure page

Reference

An Embedding is Worth a Thousand Noisy Labels - Scientific Figure on ResearchGate. Available from: https://www.researchgate.net/figure/Accuracy-on-two-clean-and-noisy-datasets-Wei-et-al-2022-The-two-best-results-are_tbl1_383429041 [accessed 27 Mar 2025]

Caption

Accuracy (↑) on two clean and noisy datasets (Wei et al., 2022). The two best results are highlighted in bold. Note that NR stands for Noise Rate. CIFAR-10N includes three annotations per image, and Noisy split denotes various aggregation strategies. Following the proposed naming convention, Aggr refers to a majority voting, R-i (i ∈ {1, 2, 3}) denotes the i-th submitted label for each image, and Worst denotes the selection of only wrong labels, if applicable. Conversely, CIFAR-100N presents just one annotation per image, thereby offering one single noisy split.

Embed code

<a href="https://www.researchgate.net/figure/Accuracy-on-two-clean-and-noisy-datasets-Wei-et-al-2022-The-two-best-results-are_tbl1_383429041"><img src="https://www.researchgate.net/publication/383429041/figure/tbl1/AS:11431281273786224@1724729802458/Accuracy-on-two-clean-and-noisy-datasets-Wei-et-al-2022-The-two-best-results-are.png" alt="Accuracy (↑) on two clean and noisy datasets (Wei et al., 2022). The two best results are highlighted in bold. Note that NR stands for Noise Rate. CIFAR-10N includes three annotations per image, and Noisy split denotes various aggregation strategies. Following the proposed naming convention, Aggr refers to a majority voting, R-i (i ∈ {1, 2, 3}) denotes the i-th submitted label for each image, and Worst denotes the selection of only wrong labels, if applicable. Conversely, CIFAR-100N presents just one annotation per image, thereby offering one single noisy split."/></a>