paper-with-me

Papers

PatchFormer: An Efficient Point Transformer with Patch Attention

2021-10-30 · CVPR 2022 1 · Zhang Cheng, Haocheng Wan, Xinyi Shen, Zizhao Wu

The point cloud learning community witnesses a modeling shift from CNNs to Transformers, where pure Transformer architectures have achieved top accuracy on the major learning benchmarks. However, existing point Transformers are computationally expensive since they need to generate a large attention map, which has quadratic complexity (both in space and time) with respect to input size. To solve this shortcoming, we introduce Patch ATtention (PAT) to adaptively learn a much smaller set of bases upon which the attention maps are computed. By a weighted summation upon these bases, PAT not only captures the global shape context but also achieves linear complexity to input size. In addition, we propose a lightweight Multi-Scale aTtention (MST) block to build attentions among features of different scales, providing the model with multi-scale features. Equipped with the PAT and MST, we construct our neural architecture called PatchFormer that integrates both modules into a joint framework for point cloud learning. Extensive experiments demonstrate that our network achieves comparable accuracy on general point cloud learning tasks with 9.2x speed-up than previous point Transformers.

📄 PDF Abstract BibTeX arXiv:2111.00207

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic Segmentation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…

Similar Papers 제목 키워드 기반

Decoding Human Attentive States from Spatial-temporal EEG Patches Using Transformers

2025-02-06 · Yi Ding, Joon Hei Lee, Shuailei Zhang, Tianze Luo 외

Learning the spatial topology of electroencephalogram (EEG) channels and their temporal dynamics is crucial for decoding attention states. This paper introduces EEG-PatchFormer, a transformer-based deep learning framewor…

Brain Computer InterfaceEEGElectroencephalogram (EEG)

Advancing Long-Term Multi-Energy Load Forecasting with Patchformer: A Patch and Transformer-Based Approach

2024-04-16 · Qiuyi Hong, Fanlin Meng, Felipe Maldonado

In the context of increasing demands for long-term multi-energy load forecasting in real-world applications, this paper introduces Patchformer, a novel model that integrates patch embedding with encoder-decoder Transform…

DecoderLoad ForecastingTime SeriesTime Series Forecasting

PatchFormer: A Patch-Based Time Series Foundation Model with Hierarchical Masked Reconstruction and Cross-Domain Transfer Learning for Zero-Shot Multi-Horizon Forecasting

2026-01-28 · Olaf Yunus Laitinen Imanov, Derya Umut Kulali, Taner Yilmaz arxiv

Time series forecasting is a fundamental problem with applications in climate, energy, healthcare, and finance. Many existing approaches require domain-specific feature engineering and substantial labeled data for each t…

Time Series ForecastingKnowledge DistillationFeature EngineeringTransfer Learning

Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classification

2022-08-26 · Xixi Wang, Xiao Wang, Bo Jiang, Bin Luo

Few-shot classification which aims to recognize unseen classes using very limited samples has attracted more and more attention. Usually, it is formulated as a metric learning problem. The core issue of few-shot classifi…

DecoderFew-Shot LearningMetric Learning

PatchFormer: A neural architecture for self-supervised representation learning on images

2019-09-25 · Aravind Srinivas, Pieter Abbeel

Learning rich representations from predictive learning without labels has been a longstanding challenge in the field of machine learning. Generative pre-training has so far not been as successful as contrastive methods i…

Representation LearningSelf-Supervised Learning