paper-with-me

홈 › Papers

Pattern Attention Transformer with Doughnut Kernel

2022-11-30 · Wenyuan Sheng

We present in this paper a new architecture, the Pattern Attention Transformer (PAT), that is composed of the new doughnut kernel. Compared with tokens in the NLP field, Transformer in computer vision has the problem of handling the high resolution of pixels in images. In ViT, an image is cut into square-shaped patches. As the follow-up of ViT, Swin Transformer proposes an additional step of shifting to decrease the existence of fixed boundaries, which also incurs 'two connected Swin Transformer blocks' as the minimum unit of the model. Inheriting the patch/window idea, our doughnut kernel enhances the design of patches further. It replaces the line-cut boundaries with two types of areas: sensor and updating, which is based on the comprehension of self-attention (named QKVA grid). The doughnut kernel also brings a new topic about the shape of kernels beyond square. To verify its performance on image classification, PAT is designed with Transformer blocks of regular octagon shape doughnut kernels. Its architecture is lighter: the minimum pattern attention layer is only one for each stage. Under similar complexity of computation, its performances on ImageNet 1K reach higher throughput (+10%) and surpass Swin Transformer (+0.8 acc1).

📄 PDF Abstract BibTeX arXiv:2211.16961

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Stochastic Depth Stochastic Depth aims to shrink the depth of a network during training, while keeping it unchanged during testing. This is achieved by randomly dropping entire…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
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 $x$…
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…

Similar Papers 제목 키워드 기반

Modelling the Doughnut of social and planetary boundaries with frugal machine learning

2025-12-01 · Stefano Vrizzi, Daniel W. O'Neill arxiv

The 'Doughnut' of social and planetary boundaries has emerged as a popular framework for assessing environmental and social sustainability. Here, we provide a proof-of-concept analysis that shows how machine learning (ML…

Reinforcement Learning

How rare are the properties of binary relations?

2022-02-10 · Ram Sewak Dubey, Giorgio Laguzzi

Knoblauch (2014) and Knoblauch (2015) investigate the relative size of the collection of binary relations with desirable features as compared to the set of all binary relations using symmetric difference metric (Cantor) …

Hilbert-Guided Sparse Local Attention

2025-11-08 · Yunge Li, Lanyu Xu arxiv

The quadratic compute and memory costs of global self-attention severely limit its use in high-resolution images. Local attention reduces complexity by restricting attention to neighborhoods. Block-sparse kernels can fur…

Impact of 3D UWB Antenna Radiation Pattern on Air-to-Ground Drone Connectivity

2018-12-17

Three dimensional (3D) radiation pattern of an antenna mounted at a drone can significantly influence the air-to-ground (A2G) link quality. Even when a drone transmitter is very close to a ground receiver, if the antenna…

Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel

2019-08-30 · EMNLP 2019 11 · Yao-Hung Hubert Tsai, Shaojie Bai, Makoto Yamada, Louis-Philippe Morency 외

Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. At the core of the Tran…

Machine TranslationTranslation