Debarshi Brahma

Amartya Bhattacharya, Debarshi Brahma, Suraj Nagaje Mahadev et al.

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 politics, sports, etc. with their unique characteristics, inference on a test image-caption pair is contingent on how well the model has been trained on similar data. Since training individual models for each domain is not practical, we propose a novel framework termed DPOD (Domain-specific Prompt tuning using Out-of-domain data), which can exploit out-of-domain data during training to improve fake news detection of all desired domains simultaneously. First, to compute generalizable features, we modify the Vision-Language Model, CLIP to extract features that helps to align the representations of the images and corresponding captions of both the in-domain and out-of-domain data in a label-aware manner. Further, we propose a domain-specific prompt learning technique which leverages training samples of all the available domains based on the extent they can be useful to the desired domain. Extensive experiments on the large-scale NewsCLIPpings and VERITE benchmarks demonstrate that DPOD achieves state of-the-art performance for this challenging task. Code: https://github.com/scviab/DPOD.

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 different classes and even domains. In this work, we take a step further and analyze whether these models can be adapted to target datasets having very different distributions and classes compared to what these models have been trained on, using only a few labeled examples from the target dataset. In such scenarios, finetuning large pretrained models is challenging due to problems of overfitting as well as loss of generalization, and has not been well explored in prior literature. Since, the pre-training data of such models are unavailable, it is difficult to comprehend the performance on various downstream datasets. First, we try to answer the question: Given a target dataset with a few labelled examples, can we estimate whether further fine-tuning can enhance the performance compared to zero-shot evaluation? by analyzing the common vision-language embedding space. Based on the analysis, we propose a novel prompt-tuning method, PromptMargin for adapting such large-scale VLMs directly on the few target samples. PromptMargin effectively tunes the text as well as visual prompts for this task, and has two main modules: 1) Firstly, we use a selective augmentation strategy to complement the few training samples in each task; 2) Additionally, to ensure robust training in the presence of unfamiliar class names, we increase the inter-class margin for improved class discrimination using a novel Multimodal Margin Regularizer. Extensive experiments and analysis across fifteen target benchmark datasets, with varying degrees of distribution shifts from natural images, shows the effectiveness of the proposed framework over the existing state-of-the-art approaches applied to this setting. github.com/debarshigit/PromptMargin.

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 often degrades when applied to target datasets with significant distribution shifts in both visual appearance and class semantics. Recent few-shot learning approaches adapt CLIP to downstream tasks using limited labeled data via adapter or prompt tuning, but are not specifically designed to handle such extreme domain shifts. Conversely, some works addressing cross-domain few-shot learning consider such domain-shifted scenarios but operate in an episodic setting with only a few classes per episode, limiting their applicability to real-world deployment, where all classes must be handled simultaneously. To address this gap, we propose a novel framework, MIST (Multiple Stochastic Prompt Tuning), for efficiently adapting CLIP to datasets with extreme distribution shifts using only a few labeled examples, in scenarios involving all classes at once. Specifically, we introduce multiple learnable prompts per class to effectively capture diverse modes in visual representations arising from distribution shifts. To further enhance generalization, these prompts are modeled as learnable Gaussian distributions, enabling efficient exploration of the prompt parameter space and reducing overfitting caused by limited supervision. Extensive experiments and comparisons with state-of-the-art methods demonstrate the effectiveness of the proposed framework.