Search Results for author:
Found 5 papers, 2 papers with code
Image Synthesis with Graph Conditioning: CLIP-Guided Diffusion Models for Scene Graphs
Existing methods approach this task by first predicting a scene layout and generating images from these layouts using adversarial training.
Language Guided Adversarial Purification
Adversarial purification using generative models demonstrates strong adversarial defense performance.
Ranked #1 on
Adversarial Defense
on CIFAR-10
(using extra training data)
IIITD-20K: Dense captioning for Text-Image ReID
IIITD-20K comprises of 20, 000 unique identities captured in the wild and provides a rich dataset for text-to-image ReID.
Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser
However, these methods suffer from high model variance with low performance on high-dimensional datasets due to the ineffective design of the denoiser and are limited in their utilization of ZO techniques.
Meta Generative Attack on Person Reidentification
Adversarial attacks have been recently investigated in person re-identification.
