TL;DR
A meta-learning-based dual-model disambiguation for partial-label learning (MD2PLL), a robust framework for candidate-label disambiguation under ambiguous annotations, is proposed and achieves competitive performance on Yahoo! News and Soccer Player.
This work proposes a novel mutual information guided reinforcement learning framework for partial label disambiguation (MR-PLL), which is formulated as a sequential Markov decision process, where an agent dynamically discriminates whether to retain, modify, or abstain from correcting ambiguous labels.
This paper formulate PML pretraining as a relation disambiguation problem and proposes a confidence-aware relation contrastive learning framework, which improves subset accuracy and F1-oriented measures under moderate and severe partial-label noise.
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.
By separating different pseudo-label reliability regions into specialized adaptation paths, TriNoL improves robustness to noisy supervision while keeping the training cost low.
G2D is proposed, a training-free framework that uses a generative VLM to verify CLIP-retrieved candidates against the image and transfers to DCLIP, WaffleCLIP, and CuPL, supporting a practical interface between discriminative proposal and generative visual reasoning.
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...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
