research
∙
08/20/2023
Strata-NeRF : Neural Radiance Fields for Stratified Scenes
Neural Radiance Field (NeRF) approaches learn the underlying 3D represen...
share
research
∙
04/28/2023
Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics
Self-training based semi-supervised learning algorithms have enabled the...
research
∙
04/20/2023
Certified Adversarial Robustness Within Multiple Perturbation Bounds
Randomized smoothing (RS) is a well known certified defense against adve...
research
∙
04/12/2023
NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs
StyleGANs are at the forefront of controllable image generation as they ...
research
∙
12/28/2022
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data
Real-world datasets exhibit imbalances of varying types and degrees. Sev...
research
∙
08/21/2022
Improving GANs for Long-Tailed Data through Group Spectral Regularization
Deep long-tailed learning aims to train useful deep networks on practica...
research
∙
08/07/2022
Hierarchical Semantic Regularization of Latent Spaces in StyleGANs
Progress in GANs has enabled the generation of high-resolution photoreal...
research
∙
06/16/2022
A Closer Look at Smoothness in Domain Adversarial Training
Domain adversarial training has been ubiquitous for achieving invariant ...
research
∙
09/18/2021
S^3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation
Unsupervised domain adaptation (DA) methods have focused on achieving ma...
research
∙
06/17/2021