3 papers
cs.CV2025
Multiple Stochastic Prompt Tuning for Few-shot Adaptation under Extreme Domain Shift
Debarshi Brahma, Soma Biswas
Foundation Vision-Language Models (VLMs) like CLIP exhibit strong generalization capabilities due to large-scale pretraining on diverse image-text pairs. However, their performance…
cs.CV2025
Prompt Tuning Vision Language Models with Margin Regularizer for Few-Shot Learning under Distribution Shifts
Debarshi Brahma, Anuska Roy, Soma Biswas
Recently, Vision-Language foundation models like CLIP and ALIGN, which are pre-trained on large-scale data have shown remarkable zero-shot generalization to diverse datasets with d…
cs.LG2025
Can Out-of-Domain data help to Learn Domain-Specific Prompts for Multimodal Misinformation Detection?
Amartya Bhattacharya, Debarshi Brahma, Suraj Nagaje Mahadev +3
Spread of fake news using out-of-context images and captions has become widespread in this era of information overload. Since fake news can belong to different domains like politic…