paper-with-me

홈 › Papers

Dual PatchNorm

2023-02-02 · Manoj Kumar, Mostafa Dehghani, Neil Houlsby

We propose Dual PatchNorm: two Layer Normalization layers (LayerNorms), before and after the patch embedding layer in Vision Transformers. We demonstrate that Dual PatchNorm outperforms the result of exhaustive search for alternative LayerNorm placement strategies in the Transformer block itself. In our experiments, incorporating this trivial modification, often leads to improved accuracy over well-tuned Vision Transformers and never hurts.

📄 PDF Abstract BibTeX arXiv:2302.01327

Code (7)

google-research/big_vision 공식 구현 jax
lucidrains/MEGABYTE-pytorch pytorch
lucidrains/denoising-diffusion-pytorch pytorch
lucidrains/musiclm-pytorch pytorch
lucidrains/phenaki-pytorch pytorch
lucidrains/recurrent-interface-network-pytorch pytorch
osier0524/lottery-ticket-to-ddpm pytorch

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Multi-Head Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

The Affine Divergence: Aligning Activation Updates Beyond Normalisation

2025-12-24 · George Bird arxiv

A systematic mismatch exists between mathematically ideal and effective activation updates during gradient descent. As intended, parameters update in their direction of steepest descent. However, activations are argued t…

Residual Networks of Residual Networks: Multilevel Residual Networks

2016-08-09 · Ke Zhang, Miao Sun, Tony X. Han, Xingfang Yuan 외

A residual-networks family with hundreds or even thousands of layers dominates major image recognition tasks, but building a network by simply stacking residual blocks inevitably limits its optimization ability. This pap…

Image Classification

Dual Learning: Theoretical Study and Algorithmic Extensions

2019-05-01 · ICLR 2019 5 · Zhibing Zhao, Yingce Xia, Tao Qin, Tie-Yan Liu

Dual learning has been successfully applied in many machine learning applications, including machine translation, image-to-image transformation, etc. The high-level idea of dual learning is very intuitive: if we map an …

Machine TranslationTranslation

Fine-grained text-driven dual-human motion generation via dynamic hierarchical interaction

2025-10-09 · Mu Li, Yin Wang, Zhiying Leng, Jiapeng Liu 외 arxiv

Human interaction is inherently dynamic and hierarchical, where the dynamic refers to the motion changes with distance, and the hierarchy is from individual to inter-individual and ultimately to overall motion. Exploitin…

Model-Level Dual Learning

2018-07-01 · ICML 2018 7 · Yingce Xia, Xu Tan, Fei Tian, Tao Qin 외

Many artificial intelligence tasks appear in dual forms like English$\leftrightarrow$French translation and speech$\leftrightarrow$text transformation. Existing dual learning schemes, which are proposed to solve a p…

Machine TranslationmodelSentiment AnalysisTranslation