Nicu Sebe, Yue Song, Ziheng Chen, Yunmei Liu
We lifted 6 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| gitzh-chen/liebn | canonical | 5 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| bimap | Ran | gitzh-chen/liebn/LieBN_SPDNet/spd/functional.py pointer only (licence: NONE) · get_code("ea89350b99bb9a1a") |
| bimap_channels | Ran | gitzh-chen/liebn/LieBN_SPDNet/spd/functional.py pointer only (licence: NONE) · get_code("4272c84c9e1317de") |
| roll | Ran | gitzh-chen/liebn/LieBN_SPDNet/cplx/functional.py pointer only (licence: NONE) · get_code("bddd9f00eeb35219") |
| split_signal_cplx | Ran | gitzh-chen/liebn/LieBN_SPDNet/cplx/functional.py pointer only (licence: NONE) · get_code("5a5a38be086e0b89") |
| trace | Ran | gitzh-chen/liebn/LieBN_SPDNet/spd/functional.py pointer only (licence: NONE) · get_code("9df6a971538219c1") |
| conv_cplx | Not yet run | gitzh-chen/liebn/LieBN_SPDNet/cplx/functional.py pointer only (licence: NONE) · get_code("1f62c02f6b6325df") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Manifold-valued measurements exist in numerous applications within computer vision and machine learning. Recent studies have extended Deep Neural Networks (DNNs) to manifolds, and concomitantly, normalization techniques have also been adapted to several manifolds, referred to as Riemannian normalization. Nonetheless, most of the existing Riemannian normalization methods have been derived in an ad hoc manner and only apply to specific manifolds. This paper establishes a unified framework for Riemannian Batch Normalization (RBN) techniques on Lie groups. Our framework offers the theoretical guarantee of controlling both the Riemannian mean and variance. Empirically, we focus on Symmetric Positive Definite (SPD) manifolds, which possess three distinct types of Lie group structures. Using the deformation concept, we generalize the existing Lie groups on SPD manifolds into three families of parameterized Lie groups. Specific normalization layers induced by these Lie groups are then proposed for SPD neural networks. We demonstrate the effectiveness of our approach through three sets of experiments: radar recognition, human action recognition, and electroencephalography (EEG) classification. The code is available at https://github.com/GitZH-Chen/LieBN.git.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.11261")
get_code_for_paper("2403.11261")
have("2403.11261")
Connect an agent — have() is free.