mlsanityData to 14 Oct 2026

Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention

arXiv 2203.03937 ↗First posted 8 Mar 2022cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by each query attending to all keys/values, various methods have constrained the range of attention within local regions, where each query only attends to keys/values within a hand-crafted window. However, these hand-crafted window partition mechanisms are data-agnostic and ignore their input content, so it is likely that one query maybe attends to irrelevant keys/values. To address this issue, we propose a Dynamic Group Attention (DG-Attention), which dynamically divides all queries into multiple groups and selects the most relevant keys/values for each group. Our DG-Attention can flexibly model more relevant dependencies without any spatial constraint that is used in hand-crafted window based attention. Built on the DG-Attention, we develop a general vision transformer backbone named Dynamic Group Transformer (DGT). Extensive experiments show that our models can outperform the state-of-the-art methods on multiple common vision tasks, including image classification, semantic segmentation, object detection, and instance segmentation.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 31 of its 37 references that are in the map. First posted on arXiv 8 Mar 2022.

Builds on

31 of 37 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2017Mask R-CNNcited by 7,277
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  10. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  11. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  12. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
19 more
  1. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  2. 2017Random Erasing Data Augmentationcited by 1,239
  3. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  4. 2016Deep Networks with Stochastic Depthcited by 979
  5. 2020Designing Network Design Spacescited by 960
  6. 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
  7. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 864
  8. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  9. 2021Transformer in Transformercited by 633
  10. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 527
  11. 2021Conditional Positional Encodings for Vision Transformerscited by 406
  12. 2021Rethinking Spatial Dimensions of Vision Transformerscited by 361
  13. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
  14. 2021Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encodingcited by 207
  15. 2021CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attentioncited by 139
  16. 2021IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformerscited by 127
  17. 2021Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformercited by 115
  18. 2021MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokenscited by 46
  19. 2021Refiner: Refining Self-attention for Vision Transformerscited by 38

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 3; 2024: 4; 2025: 2; 2026: 1.

14 papers.

Sort:

By area:

  1. 2022HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutionscited by 103
  2. 2022Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentationcited by 46
  3. 2022Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attentioncited by 35
  4. 2024Breaking the Low-Rank Dilemma of Linear Attentioncited by 31
  5. 2023Point Cloud Classification Using Content-based Transformer via Clustering in Feature Spacecited by 19
  6. 2023UniNeXt: Exploring A Unified Architecture for Vision Recognitioncited by 16
  7. 2025Rectifying Magnitude Neglect in Linear Attentioncited by 16
  8. 2024Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokenscited by 5
  9. 2023Perceptual Group Tokenizer: Building Perception with Iterative Groupingcited by 4
  10. 2024Enhancing Efficiency in Vision Transformer Networks: Design Techniques and Insightscited by 4
  11. 2022ExpNet: A unified network for Expert-Level Classificationcited by 1
  12. 2025SAC-ViT: Semantic-Aware Clustering Vision Transformer with Early Exitcited by 1
2 more
  1. 2024Not just Birds and Cars: Generic, Scalable and Explainable Models for Professional Visual Recognitioncited by 0
  2. 2026Random Wins All: Rethinking Grouping Strategies for Vision Tokenscited by 0