paper-with-me

Papers

Sparsity Aware Normalization for GANs

2021-03-03 · Idan Kligvasser, Tomer Michaeli

Generative adversarial networks (GANs) are known to benefit from regularization or normalization of their critic (discriminator) network during training. In this paper, we analyze the popular spectral normalization scheme, find a significant drawback and introduce sparsity aware normalization (SAN), a new alternative approach for stabilizing GAN training. As opposed to other normalization methods, our approach explicitly accounts for the sparse nature of the feature maps in convolutional networks with ReLU activations. We illustrate the effectiveness of our method through extensive experiments with a variety of network architectures. As we show, sparsity is particularly dominant in critics used for image-to-image translation settings. In these cases our approach improves upon existing methods, in less training epochs and with smaller capacity networks, while requiring practically no computational overhead.

📄 PDF Abstract BibTeX arXiv:2103.02458

Code (0)

등록된 구현이 없습니다.

Tasks

Image-to-Image TranslationTranslation

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…
Spectral Normalization Spectral Normalization is a normalization technique used for generative adversarial networks, used to stabilize training of the discriminator. Spectral normalization has the…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

A Systematic Survey of Regularization and Normalization in GANs

2020-08-19 · Ziqiang Li, Muhammad Usman, Rentuo Tao, Pengfei Xia 외

Generative Adversarial Networks (GANs) have been widely applied in different scenarios thanks to the development of deep neural networks. The original GAN was proposed based on the non-parametric assumption of the infini…

Data AugmentationSurvey

SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training

2026-05-26 · Mohammed Adnan, Rohan Jain, Tom Jacobs, Ekansh Sharma 외 arxiv

Dynamic Sparse Training (DST) methods train neural networks by maintaining sparsity while dynamically adapting the network topology. Despite the promise of reduced computation, DST methods converge significantly slower t…

Normalization Layers Are All That Sharpness-Aware Minimization Needs

2023-06-07 · NeurIPS 2023 11 · Maximilian Mueller, Tiffany Vlaar, David Rolnick, Matthias Hein

Sharpness-aware minimization (SAM) was proposed to reduce sharpness of minima and has been shown to enhance generalization performance in various settings. In this work we show that perturbing only the affine normalizati…

All

Mean Spectral Normalization of Deep Neural Networks for Embedded Automation

2019-07-09 · Anand Krishnamoorthy Subramanian, Nak Young Chong

Deep Neural Networks (DNNs) have begun to thrive in the field of automation systems, owing to the recent advancements in standardising various aspects such as architecture, optimization techniques, and regularization. In…

Image Generation

Gradient Normalization for Generative Adversarial Networks

2021-09-06 · ICCV 2021 10 · Yi-Lun Wu, Hong-Han Shuai, Zhi-Rui Tam, Hong-Yu Chiu

In this paper, we propose a novel normalization method called gradient normalization (GN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. Unlike existing w…