TL;DR
A novel semi-supervised framework that disentangles pseudo-label generation from the classification task via designing a dedicated pseudo-label generator to align the class distributions between labeled and unlabeled data is proposed.
DPCL was leveraged to learn better representation distributions by uniformly projecting data on a hypersphere, and by which more accurate pseudo labels could be generated, and achieves consistent improvements over existing state-of-the-art methods across multiple benchmarks.
A data-driven semi-supervised framework for imbalanced binary image classification that does not depend on data augmentation, enabling reliable utilization of unlabeled data without introducing augmentation induced noise is introduced.
Intrinsic Logit-Based Debiasing (ILBD), a robust post-hoc framework that estimates bias directly from task-relevant data without external dependencies and class priors, and effectively rectifies the classifier's bias directly from the inherent statistical patterns of the training data.
This work proposes a teacher-student semi-supervised learning framework that generates high-quality pseudo-labels from unlabeled data through confidence-aware map refinement, and introduces a spatial clipping technique that selectively preserves high-confidence regions while removing unreliable segments.
LDIBR performs instance-adaptive imputation conditioned on instance features and the binary observation mask, and learns a prior, a reliability-gated correction, and entry-wise fusion weights to produce a normalized imputed distribution.
In semi-supervised object detection (SSOD), due to the limited availability of labeled data, the quality and quantity of pseudo labels generated from unlabeled images are crucial for model training. Our study reveals that in the early stages of training, the number of usable pseudo labels is very low, which hampers the...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
