5 citations · 5 across the 3 of their papers we have counts for
5 papers
Diffusion Models with Adaptive Negative Sampling Without External Resources
Alakh Desai, Nuno Vasconcelos
Diffusion models (DMs) have demonstrated an unparalleled ability to create diverse and high-fidelity images from text prompts. However, they are also well-known to vary substantial…
Improving image synthesis with diffusion-negative sampling
Alakh Desai, Nuno Vasconcelos
For image generation with diffusion models (DMs), a negative prompt n can be used to complement the text prompt p, helping define properties not desired in the synthesized image. W…
Single-Stage Visual Relationship Learning using Conditional Queries
Alakh Desai, Tz-Ying Wu, Subarna Tripathi +1
Research in scene graph generation (SGG) usually considers two-stage models, that is, detecting a set of entities, followed by combining them and labeling all possible relationship…
Learning of Visual Relations: The Devil is in the Tails
Alakh Desai, Tz-Ying Wu, Subarna Tripathi +1
Significant effort has been recently devoted to modeling visual relations. This has mostly addressed the design of architectures, typically by adding parameters and increasing mode…
Image Segmentation Using Hybrid Representations
Alakh Desai, Ruchi Chauhan, Jayanthi Sivaswamy
This work explores a hybrid approach to segmentation as an alternative to a purely data-driven approach. We introduce an end-to-end U-Net based network called DU-Net, which uses ad…