paper-with-me

Papers

Star with Bilinear Mapping

2025-01-01 · CVPR 2025 1 · Zelin Peng, Yu Huang, Zhengqin Xu, Feilong Tang, Ming Hu, Xiaokang Yang, Wei Shen

Contextual modeling is crucial for robust visual representation learning, especially in computer vision. Although Transformers have become a leading architecture for vision tasks due to their attention mechanism, the quadratic complexity of full attention operations presents substantial computational challenges. To address this, we introduce Star with Bilinear Mapping (SBM), a Transformer-like architecture that achieves global contextual modeling with linear complexity. SBM employs a bilinear mapping module (BM) with low-rank decomposition strategy and star operations (element-wise multiplication) to efficiently capture global contextual information. Our model demonstrates competitive performance on image classification and semantic segmentation tasks, delivering significant computational efficiency gains compared to traditional attention-based models.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiencyimage-classificationImage ClassificationRepresentation LearningSemantic Segmentation

Methods 이 논문이 사용한 방법론

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 $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

STaR: Knowledge Graph Embedding by Scaling, Translation and Rotation

2022-02-15 · Jiayi Li, Yujiu Yang

The bilinear method is mainstream in Knowledge Graph Embedding (KGE), aiming to learn low-dimensional representations for entities and relations in Knowledge Graph (KG) and complete missing links. Most of the existing wo…

Graph EmbeddingKnowledge Graph EmbeddingLink PredictionTranslation

STaR: Knowledge Graph Embedding by Scaling, Translation and Rotation

2021-11-16 · ACL ARR November 2021 11 · Anonymous

The bilinear method is mainstream in Knowledge Graph Embedding (KGE), aiming to learn low-dimensional representations for entities and relations in Knowledge Graph (KG) and complete missing links. Most of the existing wo…

Graph EmbeddingKnowledge Graph EmbeddingLink PredictionTranslation

Best Arm Identification in Graphical Bilinear Bandits

2020-12-14 · Geovani Rizk, Albert Thomas, Igor Colin, Rida Laraki 외

We introduce a new graphical bilinear bandit problem where a learner (or a \emph{central entity}) allocates arms to the nodes of a graph and observes for each edge a noisy bilinear reward representing the interaction bet…

Learning to Negate Adjectives with Bilinear Models

2017-04-01 · EACL 2017 4 · Laura Rimell, Am Mabona, la, Luana Bulat 외

We learn a mapping that negates adjectives by predicting an adjective{'}s antonym in an arbitrary word embedding model. We show that both linear models and neural networks improve on this task when they have access to a …

Word Embeddings

On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging

2021-06-30 · Chris Junchi Li, Yaodong Yu, Nicolas Loizou, Gauthier Gidel 외

We study the stochastic bilinear minimax optimization problem, presenting an analysis of the same-sample Stochastic ExtraGradient (SEG) method with constant step size, and presenting variations of the method that yield f…