TL;DR
CAPSUN is proposed, a robust framework that improves the precision of clean sample selection and mitigates distribution bias through alignment among subsets, and designs a distribution alignment module to adjust the class distribution contrast of labeled and unlabeled subsets to mitigate class distribution discrepancies.
Experimental results on CIFAR-10, CIFAR-100, Animal-10N, and Mini-WebVision, together with additional evaluation under open-set noise, show that the proposed CANNE method achieves competitive performance across diverse noisy-label settings.
This paper proposes a novel Partial label-based Self-training framework (PaSta) that leverages partial label learning technique to overcome the limitations of existing methods and designs a partial label-based classification model with two well-crafted loss functions to guide the model learning at both label and repres...
This work proposes an integrated learning paradigm that simultaneously enhances feature compactness and improves robustness against label noise and introduces a feature disentanglement mechanism that isolates reliable label-related feature representations from spurious ones introduced by noisy supervision.
A general framework that constructs robust multiclass losses from univariate base functions by defining mapping operators from base functions to multiclass losses, so that the robustness of the induced losses can be characterized through simple properties of the base functions.
By separating different pseudo-label reliability regions into specialized adaptation paths, TriNoL improves robustness to noisy supervision while keeping the training cost low.
The proposed LTTL combines the power of meta-learning and self-training, achieving superior performance compared with the baseline methods on two public benchmarks, and uses the meta-learning paradigm to optimize the parameters in the whole framework.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
