Search Results for author:
Found 5 papers, 1 papers with code
iSeg: Interactive 3D Segmentation via Interactive Attention
We present iSeg, a new interactive technique for segmenting 3D shapes.
HyperFields: Towards Zero-Shot Generation of NeRFs from Text
We introduce HyperFields, a method for generating text-conditioned Neural Radiance Fields (NeRFs) with a single forward pass and (optionally) some fine-tuning.
Meta-Learning via Learning with Distributed Memory
We demonstrate that efficient meta-learning can be achieved via end-to-end training of deep neural networks with memory distributed across layers.
Domain-independent Dominance of Adaptive Methods
From a simplified analysis of adaptive methods, we derive AvaGrad, a new optimizer which outperforms SGD on vision tasks when its adaptability is properly tuned.
Scalable K-Medoids via True Error Bound and Familywise Bandits
K-Medoids(KM) is a standard clustering method, used extensively on semi-metric data. Error analyses of KM have traditionally used an in-sample notion of error, which can be far from the true error and suffer from generalization gap.
