Learning Deep Architectures via Generalized Whitened Neural Networks

By Ping Luo. 2017

46 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Concept whitening for interpretable image recognition (2020, background): “Earlier attempts whiten by periodically estimating the whitening matrix (Desjardins et al., 2015; Luo, 2017), which leads to instability in training.”
Differentiable Learning-to-Normalize via Switchable Normalization (2018, methodology): “Also, approximating the covariance matrix in a minibatch is nontrivial as discussed in (Desjardins et al., 2015; Luo, 2017b;a).”
Whitening and Coloring Batch Transform for GANs (2018, methodology): “Luo (2017) proposes to whiten the activation values using a learnable whitening matrix.”
Whitening and Coloring transform for GANs (2018, methodology): “Luo [13] proposes to whiten the activation values using a learnable whitening matrix.”
Decorrelated Batch Normalization (2018, methodology): “The proposed method in [12], however, cannot whiten the activations effectively, as shown in [34] and also discussed in Section 2.”
Normalization Techniques in Training DNNs: Methodology, Analysis and Application (2020, background): “Luo [57] investigated the effectiveness of whitening the activations (pre-whitening) and pre-activations (post-whitening).”
RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening (2021, background): “However, a number of studies [13, 14, 30, 56, 51, 36, 7, 45, 57] claim that feature covariance contains domain-speciﬁc style such as texture and color.”