activity
20242026
collaborators

7 papers

cs.CV2026

LiteEmbed: Adapting CLIP to Rare Classes

Aishwarya Agarwal, Srikrishna Karanam, Vineet Gandhi

Large-scale vision-language models such as CLIP achieve strong zero-shot recognition but struggle with classes that are rarely seen during pretraining, including newly emerging ent…

cs.CV2025

Learning 3D Texture-Aware Representations for Parsing Diverse Human Clothing and Body Parts

Kiran Chhatre, Christopher Peters, Srikrishna Karanam

Existing methods for human parsing into body parts and clothing often use fixed mask categories with broad labels that obscure fine-grained clothing types. Recent open-vocabulary s…

cs.CV2025

Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approach

Aishwarya Agarwal, Srikrishna Karanam, Vineet Gandhi

Contrastive vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition yet remain vulnerable to spurious correlations, particularly background over-reliance. W…

cs.CV2025

Composing Parts for Expressive Object Generation

Harsh Rangwani, Aishwarya Agarwal, Kuldeep Kulkarni +2

Image composition and generation are processes where the artists need control over various parts of the generated images. However, the current state-of-the-art generation models, l…

cs.CV2025

TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction

Aishwarya Agarwal, Srikrishna Karanam, Vineet Gandhi

We consider the problem of single-source domain generalization. Existing methods typically rely on extensive augmentations to synthetically cover diverse domains during training. H…

cs.CV2024

CoCoNO: Attention Contrast-and-Complete for Initial Noise Optimization in Text-to-Image Synthesis

Aravindan Sundaram, Ujjayan Pal, Abhimanyu Chauhan +2

Despite recent advancements in text-to-image models, achieving semantically accurate images in text-to-image diffusion models is a persistent challenge. While existing initial late…