mlsanityData to 14 Oct 2026

Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation

arXiv 2110.11852 ↗First posted 22 Oct 2021cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

This paper introduces a concept of layer aggregation to describe how information from previous layers can be reused to better extract features at the current layer. While DenseNet is a typical example of the layer aggregation mechanism, its redundancy has been commonly criticized in the literature. This motivates us to propose a very light-weighted module, called recurrent layer aggregation (RLA), by making use of the sequential structure of layers in a deep CNN. Our RLA module is compatible with many mainstream deep CNNs, including ResNets, Xception and MobileNetV2, and its effectiveness is verified by our extensive experiments on image classification, object detection and instance segmentation tasks. Specifically, improvements can be uniformly observed on CIFAR, ImageNet and MS COCO datasets, and the corresponding RLA-Nets can surprisingly boost the performances by 2-3% on the object detection task. This evidences the power of our RLA module in helping main CNNs better learn structural information in images.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 49 of its 62 references that are in the map. First posted on arXiv 22 Oct 2021.

Builds on

49 of 62 references.

References · 49

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2017Mask R-CNNcited by 7,277
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2016Densely Connected Convolutional Networkscited by 6,720
  7. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  8. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  9. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  10. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  11. 2017Squeeze-and-Excitation Networkscited by 4,789
  12. 2014Going Deeper with Convolutionscited by 4,241
37 more
  1. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  3. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  4. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  5. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  6. 2019Searching for MobileNetV3cited by 1,994
  7. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  8. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  9. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  10. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
  11. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  12. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  13. 2016Deep Networks with Stochastic Depthcited by 979
  14. 2014Show and Tell: A Neural Image Caption Generatorcited by 879
  15. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 575
  16. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 520
  17. 2014Long-term Recurrent Convolutional Networks for Visual Recognition and Descriptioncited by 484
  18. 2017Deep Layer Aggregationcited by 436
  19. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 431
  20. 2017Residual Attention Network for Image Classificationcited by 386
  21. 2015Visual7W: Grounded Question Answering in Imagescited by 318
  22. 2016SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioningcited by 219
  23. 2016CNN-RNN: A Unified Framework for Multi-label Image Classificationcited by 190
  24. 2018MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devicescited by 182
  25. 2021Revisiting ResNets: Improved Training and Scaling Strategiescited by 158
  26. 2018Pyramid Attention Network for Semantic Segmentationcited by 149
  27. 2017Dual Path Networkscited by 119
  28. 2020Convolutional Networks with Dense Connectivitycited by 98
  29. 2017Dilated Recurrent Neural Networkscited by 83
  30. 2016Highway and Residual Networks learn Unrolled Iterative Estimationcited by 52
  31. 2020Do RNN and LSTM have Long Memory?cited by 47
  32. 2016Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortexcited by 42
  33. 2016Architectural Complexity Measures of Recurrent Neural Networkscited by 17
  34. 2019Gated Convolutional Networks with Hybrid Connectivity for Image Classificationcited by 14
  35. 2017AOGNets: Compositional Grammatical Architectures for Deep Learningcited by 6
  36. 2017Analyzing and Exploiting NARX Recurrent Neural Networks for Long-Term Dependenciescited by 2
  37. 2016Convolutional Residual Memory Networkscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 3; 2024: 2; 2025: 3; 2026: 2.

13 papers.

Sort:

By area:

  1. 2022Dense Learning based Semi-Supervised Object Detectioncited by 32
  2. 2023Cross-Layer Retrospective Retrieving via Layer Attentioncited by 22
  3. 2024Strengthening Layer Interaction via Dynamic Layer Attentioncited by 10
  4. 2023Understanding Self-attention Mechanism via Dynamical System Perspectivecited by 9
  5. 2025Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Modelscited by 7
  6. 2022A Generic Shared Attention Mechanism for Various Backbone Neural Networkscited by 5
  7. 2021TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNscited by 4
  8. 2025HalluRNN: Mitigating Hallucinations via Recurrent Cross-Layer Reasoning in Large Vision-Language Modelscited by 4
  9. 2025Enhancing Layer Attention Efficiency through Pruning Redundant Retrievalscited by 3
  10. 2023Gramian Attention Heads are Strong yet Efficient Vision Learnerscited by 1
  11. 2024BA-Net: Bridge Attention in Deep Neural Networkscited by 0
  12. 2026Enhancing Layer Interaction Using Key-Correlated Layer Attentioncited by 0
1 more
  1. 2026Enhancing Oracle Bone Inscription Recognition via Multi-Scale Layer Attentioncited by 0