Exploiting Context for Robustness to Label Noise in Active Learning
Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are correct. However, in a practical scenario, as the quality of the labels depends on the annotator, some of the labels might be wrong, which results in degraded recognition performance. In this paper, we address the problems of i) how a system can identify which of the queried labels are wrong and ii) how a multi-class active learning system can be adapted to minimize the negative impact of label noise. Towards solving the problems, we propose a noisy label filtering based learning approach where the inter-relationship (context) that is quite common in natural data is utilized to detect the wrong labels. We construct a graphical representation of the unlabeled data to encode these relationships and obtain new beliefs on the graph when noisy labels are available. Comparing the new beliefs with the prior relational information, we generate a dissimilarity score to detect the incorrect labels and update the recognition model with correct labels which result in better recognition performance. This is demonstrated in three different applications: scene classification, activity classification, and document classification.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningDocument ClassificationGeneral ClassificationScene ClassificationSimilar Papers 제목 키워드 기반
Exploring the Robustness of In-Context Learning with Noisy Labels
Recently, the mysterious In-Context Learning (ICL) ability exhibited by Transformer architectures, especially in large language models (LLMs), has sparked significant research interest. However, the resilience of Transfo…
Data AugmentationIn-Context LearningLearning with noisy labelsRANA: Robust Active Learning for Noisy Network Alignment
Network alignment has attracted widespread attention in various fields. However, most existing works mainly focus on the problem of label sparsity, while overlooking the issue of noise in network alignment, which can sub…
Active LearningCross-Modal Consistency-Guided Active Learning for Affective BCI Systems
Deep learning models perform best with abundant, high-quality labels, yet such conditions are rarely achievable in EEG-based emotion recognition. Electroencephalogram (EEG) signals are easily corrupted by artifacts and i…
Emotion RecognitionActive LearningNoise-Adaptive Regularization for Robust Multi-Label Remote Sensing Image Classification
The development of reliable methods for multi-label classification (MLC) has become a prominent research direction in remote sensing (RS). As the scale of RS data continues to expand, annotation procedures increasingly r…
Remote Sensing Image ClassificationMulti-Label ClassificationIntroducing Fractional Classification Loss for Robust Learning with Noisy Labels
Robust loss functions are crucial for training deep neural networks in the presence of label noise, yet existing approaches require extensive, dataset-specific hyperparameter tuning. In this work, we introduce Fractional…
Learning with noisy labels