A Framework Using Contrastive Learning for Classification with Noisy Labels

Ciortan, Madalina; Dupuis, Romain; Peel, Thomas

doi:10.3390/data6060061

Cited by 8 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through the augmentation of differences between samples, CL can more clearly define classification criteria, facilitating the learning of characteristic features in challenging samples. This is highly significant for RS image classification [55,56].…”

Section: In Rs Image Processingmentioning

confidence: 99%

Unsupervised Domain Adaptation with Contrastive Learning-Based Discriminative Feature Augmentation for RS Image Classification

Xu,

Samat,

Zhu

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

High- and very high-resolution (HR, VHR) remote sensing (RS) images can provide comprehensive and intricate spatial information for land cover classification, which is particularly crucial when analyzing complex built-up environments. However, the application of HR and VHR images to large-scale and detailed land cover mapping is always constrained by the intricacy of land cover classification models, the exorbitant cost of collecting training samples, and geographical changes or acquisition conditions. To overcome this limitation, we propose an unsupervised domain adaptation (UDA) with contrastive learning-based discriminative feature augmentation (CLDFA) for RS image classification. In detail, our method first utilizes contrastive learning (CL) through a memory bank in order to memorize sample features and improve model performance, where the approach employs an end-to-end Siamese network and incorporates dynamic pseudo-label assignment and class-balancing strategies for adaptive domain joint learning. By transferring classification models trained on a source domain (SD) to an unlabeled target domain (TD), our proposed UDA method enables large-scale land cover mapping. We conducted experiments using a massive five billion-pixels dataset as the SD and tested the HR and VHR RS images of five typical Chinese cities as the TD and applied the method on the completely unlabeled world view 3 (WV3) image of Urumqi city. The experimental results demonstrate that our method excels in large-scale HR and VHR RS image classification tasks, highlighting the advantages of semantic segmentation based on end-to-end deep convolutional neural networks (DCNNs).

show abstract

Section: In Rs Image Processingmentioning

confidence: 99%

Unsupervised Domain Adaptation with Contrastive Learning-Based Discriminative Feature Augmentation for RS Image Classification

Xu,

Samat,

Zhu

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Both Cifar-10N and Cifar-100N contain 50K training images and 10k test images of size 32 × 32 × 3. Following previous works [28,37,38], two types of label noise are discussed: symmetric and asymmetric noise. Symmetric noise is derived by randomly replacing the labels with all possible labels for a certain percentage of the training data.…”

Section: Simulated Noisy Datasetsmentioning

confidence: 99%

IdentifyMix: An efficient two-stage learning approach to combating label noise

2023

J. Appl. Numer. Optim.

View full text Add to dashboard Cite

Deep neural networks require correct label annotation during supervised learning. It is inevitable, however, that some labels are noisy during the labeling process. A deep neural network retains incorrect labels during training, resulting in a degradation of performance. Therefore, it is essential to identify samples with potentially correct labels. In state-of-the-art methods, small-loss samples are chosen for subsequent training through a sample selection strategy. Howerver, it typically ignores the imbalance in noise ratios between mini-batches when performing sample selection within each minibatch. Further, numerous valuable samples with high losses are discarded, which adversely affects the generalization performance of the model, particularly under conditions of high noise ratios. To this end, this paper proposes IdentifyMix, an effective two-stage learning approach for noisy robust learning that combines an unique sample selection strategy and the semi-supervised learning technique. By observing how the dynamics of network training are changing, AUM (Area Under the Margin) provides a criterion that is applied in this research to identify mislabeled data. Moreover, by combining semi-supervised learning with contrastive learning and data augmentation, it is possible to extract more useful information from mislabeled samples. Experiments on several synthetic and real-world noise benchmarks demonstrate the effectiveness of IdentifyMix compared with state-of-the-art methods.

show abstract

Behaviour of Sample Selection Techniques Under Explicit Regularization

Lakshya

2021

Advances in Visual Computing

View full text Add to dashboard Cite

A Framework Using Contrastive Learning for Classification with Noisy Labels

Cited by 8 publications

References 36 publications

Unsupervised Domain Adaptation with Contrastive Learning-Based Discriminative Feature Augmentation for RS Image Classification

Unsupervised Domain Adaptation with Contrastive Learning-Based Discriminative Feature Augmentation for RS Image Classification

IdentifyMix: An efficient two-stage learning approach to combating label noise

Behaviour of Sample Selection Techniques Under Explicit Regularization

Contact Info

Product

Resources

About