Adaptive Sample Selection for Robust Learning under Label Noise

Patel, Deep; Sastry, P. S.

doi:10.1109/wacv56688.2023.00392

Cited by 24 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…( 7) CoDis [19]: trains two networks simultaneously and applies the covariance regularization method to maintain the divergence between the two networks. (8) Bare [48]: proposes an adaptive sample selection strategy to provide robustness against label noise.…”

Section: Comparison With Sota Methodsmentioning

confidence: 99%

CoDC: Accurate Learning with Noisy Labels via Disagreement and Consistency

Dong,

Li,

Wang

et al. 2024

Biomimetics

View full text Add to dashboard Cite

Inspired by the biological nervous system, deep neural networks (DNNs) are able to achieve remarkable performance in various tasks. However, they struggle to handle label noise, which can poison the memorization effects of DNNs. Co-teaching-based methods are popular in learning with noisy labels. These methods cross-train two DNNs based on the small-loss criterion and employ a strategy using either “disagreement” or “consistency” to obtain the divergence of the two networks. However, these methods are sample-inefficient for generalization in noisy scenarios. In this paper, we propose CoDC, a novel Co-teaching-basedmethod for accurate learning with label noise via both Disagreement and Consistency strategies. Specifically, CoDC maintains disagreement at the feature level and consistency at the prediction level using a balanced loss function. Additionally, a weighted cross-entropy loss is proposed based on information derived from the historical training process. Moreover, the valuable knowledge involved in “large-loss” samples is further developed and utilized by assigning pseudo-labels. Comprehensive experiments were conducted on both synthetic and real-world noise and under various noise types. CoDC achieved 72.81% accuracy on the Clothing1M dataset and 76.96% (Top1) accuracy on the WebVision1.0 dataset. These superior results demonstrate the effectiveness and robustness of learning with noisy labels.

show abstract

Section: Comparison With Sota Methodsmentioning

confidence: 99%

CoDC: Accurate Learning with Noisy Labels via Disagreement and Consistency

Dong,

Li,

Wang

et al. 2024

Biomimetics

View full text Add to dashboard Cite

show abstract

“…Previous literature about sample selection attempts to detect noisy labels by exacerbating the natural resistance of neural networks to noise. BARE (Patel and Sastry 2023) proposes an adaptive sample selection strategy that relies only on batch statistics to provide robustness against label noise. Another line of research focuses on label correction, which typically attempts to rectify sample labels using the model predictions.…”

Section: Related Workmentioning

confidence: 99%

Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning

Sheng,

Sun,

Cai

et al. 2024

AAAI

View full text Add to dashboard Cite

There has been significant attention devoted to the effectiveness of various domains, such as semi-supervised learning, contrastive learning, and meta-learning, in enhancing the performance of methods for noisy label learning (NLL) tasks. However, most existing methods still depend on prior assumptions regarding clean samples amidst different sources of noise (e.g., a pre-defined drop rate or a small subset of clean samples). In this paper, we propose a simple yet powerful idea called NPN, which revolutionizes Noisy label learning by integrating Partial label learning (PLL) and Negative learning (NL). Toward this goal, we initially decompose the given label space adaptively into the candidate and complementary labels, thereby establishing the conditions for PLL and NL. We propose two adaptive data-driven paradigms of label disambiguation for PLL: hard disambiguation and soft disambiguation. Furthermore, we generate reliable complementary labels using all non-candidate labels for NL to enhance model robustness through indirect supervision. To maintain label reliability during the later stage of model training, we introduce a consistency regularization term that encourages agreement between the outputs of multiple augmentations. Experiments conducted on both synthetically corrupted and real-world noisy datasets demonstrate the superiority of NPN compared to other state-of-the-art (SOTA) methods. The source code has been made available at https://github.com/NUST-Machine-Intelligence-Laboratory/NPN.

show abstract

“…• Modifying loss function to automatically ignore or to weak the emphasis on mislabeled samples along with the model training [287].…”

Section: B Improving the Generalization Ability Of Models 1) Tackling...mentioning

confidence: 99%

“…• Sample bootstrapping which provides a selection method for clean samples to update the model by recognizing clean samples as the small-loss training samples [287]:…”

Section: B Improving the Generalization Ability Of Models 1) Tackling...mentioning

confidence: 99%

Deep Learning for Automatic Vision-Based Recognition of Industrial Surface Defects: A Survey

et al. 2023

View full text Add to dashboard Cite

Automatic vision-based inspection systems have played a key role in product quality assessment for decades through the segmentation, detection, and classification of defects. Historically, machine learning frameworks, based on hand-crafted feature extraction, selection, and validation, counted on a combined approach of parameterized image processing algorithms and explicated human knowledge. The outstanding performance of deep learning (DL) for vision systems, in automatically discovering a feature representation suitable for the corresponding task, has exponentially increased the number of scientific articles and commercial products aiming at industrial quality assessment. In such a context, this article reviews more than 220 relevant articles from the related literature published until February 2023, covering the recent consolidation and advances in the field of fully-automatic DL-based surface defects inspection systems, deployed in various industrial applications. The analyzed papers have been classified according to a bi-dimensional taxonomy, that considers both the specific defect recognition task and the employed learning paradigm. The dependency on large and high-quality labeled datasets and the different neural architectures employed to achieve an overall perception of both well-visible and subtle defects, through the supervision of fine or/and coarse data annotations have been assessed. The results of our analysis highlight a growing research interest in defect representation power enrichment, especially by transferring pre-trained layers to an optimized network and by explaining the network decisions to suggest trustworthy retention or rejection of the products being evaluated.

show abstract

Adaptive Sample Selection for Robust Learning under Label Noise

Cited by 24 publications

References 33 publications

CoDC: Accurate Learning with Noisy Labels via Disagreement and Consistency

CoDC: Accurate Learning with Noisy Labels via Disagreement and Consistency

Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning

Deep Learning for Automatic Vision-Based Recognition of Industrial Surface Defects: A Survey

Contact Info

Product

Resources

About