7 papers · 1 filter
BiPrompt: Bilateral Prompt Optimization for Visual and Textual Debiasing in Vision-Language Models
Sunny Gupta, Shounak Das, Amit Sethi
Vision language foundation models such as CLIP exhibit impressive zero-shot generalization yet remain vulnerable to spurious correlations across visual and textual modalities. Exis…
CCVA-FL: Cross-Client Variations Adaptive Federated Learning for Medical Imaging
Sunny Gupta, Amit Sethi
Federated Learning (FL) offers a privacy-preserving approach to train models on decentralized data. Its potential in healthcare is significant, but challenges arise due to cross-cl…
Federated Cross-Modal Style-Aware Prompt Generation
Suraj Prasad, Navyansh Mahla, Sunny Gupta +1
Prompt learning has propelled vision-language models like CLIP to excel in diverse tasks, making them ideal for federated learning due to computational efficiency. However, convent…
Which Backbone to Use: A Resource-efficient Domain Specific Comparison for Computer Vision
Pranav Jeevan, Amit Sethi
In contemporary computer vision applications, particularly image classification, architectural backbones pre-trained on large datasets like ImageNet are commonly employed as featur…
FLD+: Data-efficient Evaluation Metric for Generative Models
Pranav Jeevan, Neeraj Nixon, Amit Sethi
We introduce a new metric to assess the quality of generated images that is more reliable, data-efficient, compute-efficient, and adaptable to new domains than the previous metrics…
Normalizing Flow-Based Metric for Image Generation
Pranav Jeevan, Neeraj Nixon, Amit Sethi
We propose two new evaluation metrics to assess realness of generated images based on normalizing flows: a simpler and efficient flow-based likelihood distance (FLD) and a more exa…