# Active Learning for Vision-Language Models Source: [Active Learning for Vision-Language Models]() Collection index: [llms.txt]() Data updated: 2025-10-26T03:33:53.801Z Authors: Bardia Safaei, Vishal M. Patel Published: 2024-10-29T16:25:50.000Z ## Abstract Pre-trained vision-language models (VLMs) like CLIP have demonstrated impressive zero-shot performance on a wide range of downstream computer vision tasks. However, there still exists a considerable performance gap between these models and a supervised deep model trained on a downstream dataset. To bridge this gap, we propose a novel active learning (AL) framework that enhances the zero-shot classification performance of VLMs by selecting only a few informative samples from the unlabeled data for annotation during training. To achieve this, our approach first calibrates the predicted entropy of VLMs and then utilizes a combination of self-uncertainty and neighbor-aware uncertainty to calculate a reliable uncertainty measure for active sample selection. Our extensive experiments show that the proposed approach outperforms existing AL approaches on several image classification datasets, and significantly enhances the zero-shot performance of VLMs. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on UCF101](): Image Classification; UCF101; Top-1 Acc: 78. - [Image Classification on DTD (Accuracy)](): Image Classification; DTD; Accuracy: 63.7. - [Image Classification on Flowers102](): Image Classification; Flowers102; Accuracy: 86.5. ## Original sources and implementation [Original paper]() [PDF]()