Post-hoc Probabilistic Vision-Language Models

A Baumann, R Li, M Klasson, S Mentu, S Karthik… - arxiv preprint arxiv …, 2024 - arxiv.org
Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success
in classification, retrieval, and generative tasks. For this, VLMs deterministically map images …

Active Prompt Learning with Vision-Language Model Priors

H Kim, S **, C Sung, J Kim, J Ok - arxiv preprint arxiv:2411.16722, 2024 - arxiv.org
Vision-language models (VLMs) have demonstrated remarkable zero-shot performance
across various classification tasks. Nonetheless, their reliance on hand-crafted text prompts …

Parameter-Efficient Active Learning for Foundational models

AL Narayanan, R Krishnan, A Machireddy… - arxiv preprint arxiv …, 2024 - arxiv.org
Foundational vision transformer models have shown impressive few shot performance on
many vision tasks. This research presents a novel investigation into the application of …

ACTIVE TEST TIME PROMPT LEARNING IN VISION-LANGUAGE MODELS

D Sarkar, A Chakrabartty, B Bhanja, A Das - openreview.net
Test Time Optimisation is a setting where a model is made to learn new parameters on-the-
fly during inference with the help of those very samples it is supposed to be tested on …

Probabilistic Active Few-Shot Learning in Vision-Language Models

A Baumann, M Klasson, R Li, A Solin… - Workshop on Responsibly … - openreview.net
Pre-trained vision-language models (VLMs) have shown to be an useful model class for
zero-and few-shot learning tasks. In this work, we investigate probabilistic active few-shot …