Lune

CVPR2025Top-tier venue

Star with Bilinear Mapping

Zelin Peng, Yu Huang, Zhengqin Xu, Feilong Tang, Ming Hu, Xiaokang Yang, Wei Shen

Abstract

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. Code is available at https://github.com/SJTU- DeepVisionLab/SBM .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale cites Language Models are Few-Shot Learners
  • Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites Learning Transferable Visual Models From Natural Language Supervision
  • Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites Training data-efficient image transformers & distillation through attention
  • Unlocking 3D Affordance Segmentation with 2D Semantic Knowledge cites Learning Transferable Visual Models From Natural Language Supervision
  • Learning Transferable Visual Models From Natural Language Supervision cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • Learning Transferable Visual Models From Natural Language Supervision cites Language Models are Few-Shot Learners
  • Training data-efficient image transformers & distillation through attention cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-FreeZihan Qiu, Zekun Wang, Bo Zheng, Zeyu Huang et al.NeurIPS 2025 · 336 citations
  2. Unlocking 3D Affordance Segmentation with 2D Semantic KnowledgeYu Huang, Zelin Peng, Changsong Wen, Xiaokang Yang et al.CVPR 2026 · 3 citations

Builds on33

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
  3. Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu et al.ICCV 2021 · 31,683 citations
  4. An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
  5. Training data-efficient image transformers & distillation through attentionHugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa et al.ICML 2021 · 8,974 citations

Related papers

  1. Orthogonal Transformer: An Efficient Vision Transformer Backbone with Token OrthogonalizationHuaibo Huang, Xiaoqiang Zhou, Ran HeNeurIPS 2022 · 35 citations
  2. Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer InferenceHaoran You, Yunyang Xiong, Xiaoliang Dai, Bichen Wu et al.CVPR 2023
  3. XCiT: Cross-Covariance Image TransformersAlaaeldin Ali, Hugo Touvron, Mathilde Caron, Piotr Bojanowski et al.NeurIPS 2021 · 692 citations
  4. Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped AttentionSitong Wu, Tianyi Wu, Haoru Tan, Guodong GuoAAAI 2022 · 84 citations
  5. FLatten Transformer: Vision Transformer using Focused Linear AttentionDongchen Han, Xuran Pan, Yizeng Han, Shiji Song et al.ICCV 2023 · 358 citations
Dusk over the sea between two cliffs drawn in fine vertical lines