{"ID":2889060,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.21521","arxiv_id":"2507.21521","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","abstract":"Active Learning (AL) has emerged as a powerful approach for minimizing labeling costs by selectively sampling the most informative data for neural network model development. Effective AL for large-scale vision-language models necessitates addressing challenges in uncertainty estimation and efficient sampling given the vast number of parameters involved. In this work, we introduce a novel parameter-efficient learning methodology that incorporates uncertainty calibration loss within the AL framework. We propose a differentiable loss function that promotes uncertainty calibration for effectively selecting fewer and most informative data samples for fine-tuning. Through extensive experiments across several datasets and vision backbones, we demonstrate that our solution can match and exceed the performance of complex feature-based sampling techniques while being computationally very efficient. Additionally, we investigate the efficacy of Prompt learning versus Low-rank adaptation (LoRA) in sample selection, providing a detailed comparative analysis of these methods in the context of efficient AL.","short_abstract":"Active Learning (AL) has emerged as a powerful approach for minimizing labeling costs by selectively sampling the most informative data for neural network model development. Effective AL for large-scale vision-language models necessitates addressing challenges in uncertainty estimation and efficient sampling given the...","url_abs":"https://arxiv.org/abs/2507.21521","url_pdf":"https://arxiv.org/pdf/2507.21521v1","authors":"[\"Athmanarayanan Lakshmi Narayanan\",\"Amrutha Machireddy\",\"Ranganath Krishnan\"]","published":"2025-07-29T06:08:28Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\",\"LoRA\"]","has_code":false}