Lune

CVPR2026Top-tier venue

Convolutional Neural Networks Driven by Content Similarity

Ligeng Zou, Guihu Zhao

Abstract

Although convolutional neural networks (CNNs) have continued to evolve in recent years, Transformers have become increasingly popular in the field of computer vision. In this work, we introduce a mechanism for CNNs to aggregate information based on content similarity-an ability analogous to the self-attention mechanism. We achieve this by proposing a sorting operation that transforms the feature similarity between tokens into relative positional information: specifically, rearranging tokens such that tokens with higher feature similarity are placed closer together. This approach allows convolution operations to be indirectly transformed into an aggregation mode driven by content similarity. Experiments show that our proposed model, named Ego, achieves promising results across various tasks, underscoring the untapped potential of CNNs. Code and models are publicly available at https:// github.com/essenceoftheworld/ego.

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.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • A ConvNet for the 2020s cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • A ConvNet for the 2020s cites Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
  • A ConvNet for the 2020s cites Training data-efficient image transformers & distillation through attention
  • 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 Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
  • Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites Training data-efficient image transformers & distillation through attention
  • Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions cites Training data-efficient image transformers & distillation through attention
  • 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.

Builds on29

  1. Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu et al.ICCV 2021 · 31,683 citations
  2. 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
  3. Training data-efficient image transformers & distillation through attentionHugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa et al.ICML 2021 · 8,974 citations
  4. A ConvNet for the 2020sZhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer et al.CVPR 2022 · 6,782 citations
  5. Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without ConvolutionsWenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan et al.ICCV 2021 · 4,909 citations

Related papers

  1. Building Vision Transformers with Hierarchy Aware Feature AggregationYongjie Chen, Hongmin Liu, Haoran Yin, Bin FanICCV 2023 · 6 citations
  2. Container: Context Aggregation NetworksPeng Gao, Jiasen Lu, Hongsheng Li, Roozbeh Mottaghi et al.NeurIPS 2021 · 86 citations
  3. Efficient Equivariant NetworkLingshen He, Yuxuan Chen, Zhengyang Shen, Yiming Dong et al.NeurIPS 2021 · 46 citations
  4. ConViT: Improving Vision Transformers with Soft Convolutional Inductive BiasesStéphane d'Ascoli, Hugo Touvron, Matthew L. Leavitt, Ari S. Morcos et al.ICML 2021 · 1,021 citations
  5. CATs: Cost Aggregation Transformers for Visual CorrespondenceSeokju Cho, Sunghwan Hong, Sangryul Jeon, Yunsung Lee et al.NeurIPS 2021 · 133 citations
Dusk over the sea between two cliffs drawn in fine vertical lines