30 citations · 81 across the 13 of their papers we have counts for
21 papers
Heterogeneous Continual Learning
Divyam Madaan, Hongxu Yin, Wonmin Byeon +2
We propose a novel framework and a solution to tackle the continual learning (CL) problem with changing network architectures. Most CL methods focus on adapting a single architectu…
RANA: Relightable Articulated Neural Avatars
Umar Iqbal, Akin Caliskan, Koki Nagano +3
We propose RANA, a relightable and articulated neural avatar for the photorealistic synthesis of humans under arbitrary viewpoints, body poses, and lighting. We only require a shor…
Structural Pruning via Latency-Saliency Knapsack
Maying Shen, Hongxu Yin, Pavlo Molchanov +3
Structural pruning can simplify network architecture and improve inference speed. We propose Hardware-Aware Latency Pruning (HALP) that formulates structural pruning as a global re…
DRaCoN -- Differentiable Rasterization Conditioned Neural Radiance Fields for Articulated Avatars
Amit Raj, Umar Iqbal, Koki Nagano +4
Acquisition and creation of digital human avatars is an important problem with applications to virtual telepresence, gaming, and human modeling. Most contemporary approaches for av…
GradViT: Gradient Inversion of Vision Transformers
Ali Hatamizadeh, Hongxu Yin, Holger Roth +4
In this work we demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. During this attack, the original data batch is reconstructed given…
When to Prune? A Policy towards Early Structural Pruning
Maying Shen, Pavlo Molchanov, Hongxu Yin +1
Pruning enables appealing reductions in network memory footprint and time complexity. Conventional post-training pruning techniques lean towards efficient inference while overlooki…