2025/05/08 by Aishwarya Venkataramanan, Venkataramanan, Aishwarya, Paul Bodesheim +3 · 2 citations
Computer Science · Social Sciences · #AI-based Problem Solving and Planning #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Geographic Information Systems Studies #Machine Learning (cs.LG) #Semantic Web and Ontologies
paper · pdf · doi:10.48550/arxiv.2505.05163
openalex publication_date 2025/05/08 · openalex created_date 2025/10/20 · openalex updated_date 2026/07/28
Vision-Language Models (VLMs) learn joint representations by mapping images and text into a shared latent space. However, recent research highlights that deterministic embeddings from standard VLMs often struggle to capture the uncertainties arising from the ambiguities in visual and textual descriptions and the multiple possible correspondences between images and texts. Existing approaches tackle this by learning probabilistic embeddings during VLM training, which demands large datasets and does not leverage the powerful representations already learned by large-scale VLMs like CLIP. In this paper, we propose GroVE, a post-hoc approach to obtaining probabilistic embeddings from frozen VLMs. GroVE builds on Gaussian Process Latent Variable Model (GPLVM) to learn a shared low-dimensional latent space where image and text inputs are mapped to a unified representation, optimized through single-modal embedding reconstruction and cross-modal alignment objectives. Once trained, the Gaussian Process model generates uncertainty-aware probabilistic embeddings. Evaluation shows that GroVE achieves state-of-the-art uncertainty calibration across multiple downstream tasks, including cross-modal retrieval, visual question answering, and active learning.