mlsanityData to 7 Oct 2026

Squeeze-and-Excitation Networks

arXiv 1709.01507 ↗First posted 5 Sep 2017cs.CVcited by 4,763

Not on the map. Why?

Cited by 67 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and channel-wise information within local receptive fields at each layer. A broad range of prior research has investigated the spatial component of this relationship, seeking to strengthen the representational power of a CNN by enhancing the quality of spatial encodings throughout its feature hierarchy. In this work, we focus instead on the channel relationship and propose a novel architectural unit, which we term the "Squeeze-and-Excitation" (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. We show that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets. We further demonstrate that SE blocks bring significant improvements in performance for existing state-of-the-art CNNs at slight additional computational cost. Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2.251%, surpassing the winning entry of 2016 by a relative improvement of ~25%. Models and code are available at https://github.com/hujie-frank/SENet.

Key facts. Cited by 4,763 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Sep 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 2; 2020: 1; 2021: 1083; 2022: 946; 2023: 828; 2024: 742; 2025: 659; 2026: 502.

4,763 papers.

Sort:

By area:

  1. 2022A ConvNet for the 2020scited by 3,545
  2. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  3. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  4. 2021ViViT: A Video Vision Transformercited by 1,610
  5. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  6. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  7. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  8. 2021Multi-Stage Progressive Image Restorationcited by 813
  9. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  10. 2021Going deeper with Image Transformerscited by 759
  11. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  12. 2022Simple Baselines for Image Restorationcited by 701
38 more
  1. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 636
  2. 2021Transformer in Transformercited by 632
  3. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  4. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 566
  5. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  6. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  7. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 549
  8. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  9. 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
  10. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Modelscited by 482
  11. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  12. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  13. 2021Conditional DETR for Fast Training Convergencecited by 422
  14. 2021Dynamic Neural Networks: A Surveycited by 405
  15. 2022Decoupled Knowledge Distillationcited by 380
  16. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  17. 2021Pay Attention to MLPscited by 367
  18. 2021ResNet strikes back: An improved training procedure in timmcited by 365
  19. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  20. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 359
  21. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 349
  22. 2021LAVT: Language-Aware Vision Transformer for Referring Image Segmentationcited by 347
  23. 2021XCiT: Cross-Covariance Image Transformerscited by 335
  24. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  25. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
  26. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  27. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
  28. 2021Distilling Knowledge via Knowledge Reviewcited by 285
  29. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  30. 2021Generalizing Face Forgery Detection with High-frequency Featurescited by 261
  31. 2021Escaping the Big Data Paradigm with Compact Transformerscited by 261
  32. 2021TransFuse: Fusing Transformers and CNNs for Medical Image Segmentationcited by 258
  33. 2021Knowledge distillation: A good teacher is patient and consistentcited by 255
  34. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  35. 2021Understanding Robustness of Transformers for Image Classificationcited by 250
  36. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
  37. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  38. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242

50 most cited of 4,763 All 4,763 (JSON)