Research map / Label-efficient and robust learning / Semi-supervised learning

Progressive Pseudo-label Self-balancing Towards Unsupervised Vision-Language Models Adaptation

NeurIPS 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Addresses long-tailed pseudo-label bias when adapting vision-language models with unlabeled data by progressively self-balancing pseudo-labels across classes.

Problem

VLMs' inherent class-wise prediction bias yields long-tailed pseudo-labels that mismatch the true label distribution when adapting with unlabeled data.

Approach

Divides classes into groups by pseudo-label frequency and progressively self-balances the pseudo-labeled set so that generated labels better match the true label distribution; only the abstract is available, so details are limited.

Closest papers by meaning

• Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin (ICML 2025 · similarity 0.92)
• Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data (ICML 2024 · similarity 0.92)
• Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model (ICLR 2025 · similarity 0.89)
• Pre-Trained Vision-Language Models as Noisy Partial Annotators (AAAI 2025 · similarity 0.89)
• Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt Learning (CVPR 2025 · similarity 0.88)
• Efficient Test-Time Adaptation of Vision-Language Models (CVPR 2024 · similarity 0.88)