Search Results for author:
Found 6 papers, 4 papers with code
LightAvatar: Efficient Head Avatar as Dynamic Neural Light Field
Recent works have shown that neural radiance fields (NeRFs) on top of parametric models have reached SOTA quality to build photorealistic head avatars from a monocular video.
On the Efficacy of Multi-scale Data Samplers for Vision Applications
Multi-scale resolution training has seen an increased adoption across multiple vision tasks, including classification and detection.
SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks
In this paper, we perform an empirical evaluation on methods for sharing parameters in isotropic networks (SPIN).
LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time
Our models require no retraining, thus our subspace of models can be deployed entirely on-device to allow adaptive network compression at inference time.
Token Pooling in Vision Transformers
Token Pooling is a simple and effective operator that can benefit many architectures.
Butterfly Transform: An Efficient FFT Based Neural Architecture Design
By replacing pointwise convolutions with BFT, we reduce the computational complexity of these layers from O(n^2) to O(n\log n) with respect to the number of channels.
