Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Does Marginal Coverage Guarantee Class-Conditional Safety for Zero-Shot VLMs Under Shift?
Jai Kumar Sharma, Amartya Dutta
Split-conformal prediction provides marginal coverage under exchangeability and is increasingly used as an abstention layer for zero-shot vision-language models (VLMs). We audit th…
cs.CV2025
Open World Scene Graph Generation using Vision Language Models
Amartya Dutta, Kazi Sajeed Mehrab, Medha Sawhney +8
Scene-Graph Generation (SGG) seeks to recognize objects in an image and distill their salient pairwise relationships. Most methods depend on dataset-specific supervision to learn t…
cs.CV2023
Beyond Discriminative Regions: Saliency Maps as Alternatives to CAMs for Weakly Supervised Semantic Segmentation
M. Maruf, Arka Daw, Amartya Dutta +2
In recent years, several Weakly Supervised Semantic Segmentation (WS3) methods have been proposed that use class activation maps (CAMs) generated by a classifier to produce pseudo-…