4 papers
Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation
Sanyam Lakhanpal, Shivang Chopra, Vinija Jain +2
Over the past few years, Text-to-Image (T2I) generation approaches based on diffusion models have gained significant attention. However, vanilla diffusion models often suffer from…
Source-Free Domain Adaptation with Diffusion-Guided Source Data Generation
Shivang Chopra, Suraj Kothawade, Houda Aynaou +1
This paper introduces a novel approach to leverage the generalizability of Diffusion Models for Source-Free Domain Adaptation (DM-SFDA). Our proposed DMSFDA method involves fine-tu…
Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning
Sachit Kuhar, Shuo Cheng, Shivang Chopra +2
Practical Imitation Learning (IL) systems rely on large human demonstration datasets for successful policy learning. However, challenges lie in maintaining the quality of collected…
Transcending Domains through Text-to-Image Diffusion: A Source-Free Approach to Domain Adaptation
Shivang Chopra, Suraj Kothawade, Houda Aynaou +1
Domain Adaptation (DA) is a method for enhancing a model's performance on a target domain with inadequate annotated data by applying the information the model has acquired from a r…