Papers › Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
Zhilu Zhang, Mert R. Sabuncu
Deep neural networks (DNNs) have achieved tremendous success in a variety of applications across many disciplines. Yet, their superior performance comes with the expensive cost of requiring correctly annotated large-scale datasets. Moreover, due to DNNs' rich capacity, errors in training labels can hamper performance. To combat this problem, mean absolute error (MAE) has recently been proposed as a noise-robust alternative to the commonly-used categorical cross entropy (CCE) loss. However, as we show in this paper, MAE can perform poorly with DNNs and challenging datasets. Here, we present a theoretically grounded set of noise-robust loss functions that can be seen as a generalization of MAE and CCE. Proposed loss functions can be readily applied with any existing DNN architecture and algorithm, while yielding good performance in a wide range of noisy label scenarios. We report results from experiments conducted with CIFAR-10, CIFAR-100 and FASHION-MNIST datasets and synthetically generated noisy labels.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="1805.07836", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1805.07836")
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Classification | Clothing1M | GCE | Accuracy | 69.75% | #49 of 51 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-100N | GCE | Accuracy (mean) | 56.73 | #20 of 24 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Aggregate | GCE | Accuracy (mean) | 87.85 | #25 of 26 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Random1 | GCE | Accuracy (mean) | 87.61 | #22 of 24 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Random2 | GCE | Accuracy (mean) | 87.70 | #20 of 23 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Random3 | GCE | Accuracy (mean) | 87.58 | #20 of 23 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Worst | GCE | Accuracy (mean) | 80.66 | #20 of 25 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections