mlsanityData to 7 Oct 2026

Designing Network Design Strategies Through Gradient Path Analysis

arXiv 2211.04800 ↗First posted 9 Nov 2022cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

Designing a high-efficiency and high-quality expressive network architecture has always been the most important research topic in the field of deep learning. Most of today's network design strategies focus on how to integrate features extracted from different layers, and how to design computing units to effectively extract these features, thereby enhancing the expressiveness of the network. This paper proposes a new network design strategy, i.e., to design the network architecture based on gradient path analysis. On the whole, most of today's mainstream network design strategies are based on feed forward path, that is, the network architecture is designed based on the data path. In this paper, we hope to enhance the expressive ability of the trained model by improving the network learning ability. Due to the mechanism driving the network parameter learning is the backward propagation algorithm, we design network design strategies based on back propagation path. We propose the gradient path design strategies for the layer-level, the stage-level, and the network-level, and the design strategies are proved to be superior and feasible from theoretical analysis and experiments.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 31 of its 40 references that are in the map. First posted on arXiv 9 Nov 2022.

Builds on

31 of 40 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  7. 2014Going Deeper with Convolutionscited by 4,231
  8. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  9. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  10. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  11. 2018YOLOv3: An Incremental Improvementcited by 2,652
  12. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
19 more
  1. 2019Searching for MobileNetV3cited by 1,984
  2. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  3. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  4. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  5. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  6. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  7. 2016Deep Networks with Stochastic Depthcited by 973
  8. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 719
  9. 2019Selective Kernel Networkscited by 401
  10. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  11. 2019Dynamic Convolution: Attention over Convolution Kernelscited by 355
  12. 2016FractalNet: Ultra-Deep Neural Networks without Residualscited by 216
  13. 2020Scaled-YOLOv4: Scaling Cross Stage Partial Networkcited by 211
  14. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 200
  15. 2019An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detectioncited by 163
  16. 2017Receptive Field Block Net for Accurate and Fast Object Detectioncited by 140
  17. 2020Disentangled Non-Local Neural Networkscited by 132
  18. 2021You Only Learn One Representation: Unified Network for Multiple Taskscited by 86
  19. 2019Dually Supervised Feature Pyramid for Object Detection and Segmentationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 16; 2025: 6; 2026: 2.

32 papers.

Sort:

  1. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  2. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  3. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 300
  4. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
  5. 2024DRCT: Saving Image Super-resolution away from Information Bottleneckcited by 40
  6. 2023YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detectioncited by 33
  7. 2024Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computationcited by 29
  8. 2024YOLOv9 for Fracture Detection in Pediatric Wrist Trauma X-ray Imagescited by 10
  9. 2024YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detectioncited by 7
  10. 2024YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systemscited by 6
  11. 2023RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detectioncited by 5
  12. 2023YOLOR-Based Multi-Task Learningcited by 5
20 more
  1. 2024SOAR: Advancements in Small Body Object Detection for Aerial Imagery Using State Space Models and Programmable Gradientscited by 5
  2. 2024YOLOv8-ResCBAM: YOLOv8 Based on An Effective Attention Module for Pediatric Wrist Fracture Detectioncited by 5
  3. 2023YOLOCS: Object Detection based on Dense Channel Compression for Feature Spatial Solidificationcited by 4
  4. 2024Iterative Filter Pruning for Concatenation-based CNN Architecturescited by 4
  5. 2024What is YOLOv9: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detectorcited by 4
  6. 2025A Decade of You Only Look Once (YOLO) for Object Detection: A Reviewcited by 3
  7. 2024FedPylot: Navigating Federated Learning for Real-Time Object Detection in Internet of Vehiclescited by 2
  8. 2024Finetuning YOLOv9 for Vehicle Detection: Deep Learning for Intelligent Transportation Systems in Dhaka, Bangladeshcited by 2
  9. 2025Performance Optimization of YOLO-FEDER FusionNet for Robust Drone Detection in Visually Complex Environmentscited by 2
  10. 2023Underwater target detection based on improved YOLOv7cited by 1
  11. 2023CST-YOLO: A Novel Method for Blood Cell Detection Based on Improved YOLOv7 and CNN-Swin Transformercited by 1
  12. 2024PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slicescited by 1
  13. 2025Real-time Video Prediction With Fast Video Interpolation Model and Prediction Trainingcited by 1
  14. 2023Q-YOLOP: Quantization-aware You Only Look Once for Panoptic Driving Perceptioncited by 0
  15. 2024RepVGG-GELAN: Enhanced GELAN with VGG-STYLE ConvNets for Brain Tumour Detectioncited by 0
  16. 2024YOLO-ELA: Efficient Local Attention Modeling for High-Performance Real-Time Insulator Defect Detectioncited by 0
  17. 2025YOLO-PRO: Enhancing Instance-Specific Object Detection with Full-Channel Global Self-Attentioncited by 0
  18. 2025Two-Stage Framework for Efficient UAV-Based Wildfire Video Analysis with Adaptive Compression and Fire Source Detectioncited by 0
  19. 2026N-EIoU-YOLOv9: A Signal-Aware Bounding Box Regression Loss for Lightweight Mobile Detection of Rice Leaf Diseasescited by 0
  20. 2026FD-CanKD: Frequency-Decoupled Cross-Attention Distillation as a Refinement Prior for Compact Object Detectorscited by 0