mlsanityData to 7 Oct 2026

Densely Connected Convolutional Networks

arXiv 1608.06993 ↗First posted 25 Aug 2016cs.CV cs.LGcited by 6,691

Not on the map. Why?

Cited by 105 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections - one between each layer and its subsequent layer - our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet .

Key facts. Cited by 6,691 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Aug 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 2; 2019: 0; 2020: 0; 2021: 1587; 2022: 1352; 2023: 1266; 2024: 1046; 2025: 909; 2026: 529.

6,691 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2022A ConvNet for the 2020scited by 3,545
  3. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  4. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  5. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  6. 2021Video Swin Transformercited by 1,090
  7. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
  8. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  9. 2024VMamba: Visual State Space Modelcited by 955
  10. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  11. 2021Multi-Stage Progressive Image Restorationcited by 813
  12. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
38 more
  1. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  2. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  3. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 685
  4. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 636
  5. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 619
  6. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  7. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
  8. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  9. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  10. 2021Fast Model Editing at Scalecited by 491
  11. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  12. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  13. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  14. 2021Dynamic Neural Networks: A Surveycited by 405
  15. 2023DIRE for Diffusion-Generated Image Detectioncited by 386
  16. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  17. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  18. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 351
  19. 2021Multi-attentional Deepfake Detectioncited by 339
  20. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  21. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  22. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
  23. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  24. 2021ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networkscited by 293
  25. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 292
  26. 2021DeepViT: Towards Deeper Vision Transformercited by 288
  27. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  28. 2021An Empirical Study of Training End-to-End Vision-and-Language Transformerscited by 271
  29. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  30. 2021Gradient Matching for Domain Generalizationcited by 258
  31. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  32. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  33. 2021Understanding Robustness of Transformers for Image Classificationcited by 250
  34. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
  35. 2022Transformers in Medical Imaging: A Surveycited by 245
  36. 2021LocalViT: Analyzing Locality in Vision Transformerscited by 228
  37. 2021A Geometric Analysis of Neural Collapse with Unconstrained Featurescited by 226
  38. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216

50 most cited of 6,691 All 6,691 (JSON)