mlsanityData to 14 Oct 2026

PolyNet: A Pursuit of Structural Diversity in Very Deep Networks

arXiv 1611.05725 ↗First posted 17 Nov 2016cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

A number of studies have shown that increasing the depth or width of convolutional networks is a rewarding approach to improve the performance of image recognition. In our study, however, we observed difficulties along both directions. On one hand, the pursuit for very deep networks is met with a diminishing return and increased training difficulty; on the other hand, widening a network would result in a quadratic growth in both computational cost and memory demand. These difficulties motivate us to explore structural diversity in designing deep networks, a new dimension beyond just depth and width. Specifically, we present a new family of modules, namely the PolyInception, which can be flexibly inserted in isolation or in a composition as replacements of different parts of a network. Choosing PolyInception modules with the guidance of architectural efficiency can improve the expressive power while preserving comparable computational cost. The Very Deep PolyNet, designed following this direction, demonstrates substantial improvements over the state-of-the-art on the ILSVRC 2012 benchmark. Compared to Inception-ResNet-v2, it reduces the top-5 validation error on single crops from 4.9% to 4.25%, and that on multi-crops from 3.7% to 3.45%.

Key facts. Cited by 39 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 17; 2022: 7; 2023: 4; 2024: 3; 2025: 6; 2026: 2.

39 papers.

Sort:

By area:

  1. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 249
  2. 2021Encoding physics to learn reaction-diffusion processescited by 61
  3. 2022ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generationcited by 27
  4. 2021ODE Transformer: An Ordinary Differential Equation-Inspired Model for Neural Machine Translationcited by 12
  5. 2021Exercise? I thought you said 'Extra Fries': Leveraging Sentence Demarcations and Multi-hop Attention for Meme Affect Analysiscited by 9
  6. 2021An Interpretive Constrained Linear Model for ResNet and MgNetcited by 6
  7. 2022Semantic Segmentation using Neural Ordinary Differential Equationscited by 6
  8. 2021Diffusion Mechanism in Residual Neural Network: Theory and Applicationscited by 5
  9. 2022An Interpretable MRI Reconstruction Network with Two-grid-cycle Correction and Geometric Prior Distillationcited by 5
  10. 2021Low-cost and high-performance data augmentation for deep-learning-based skin lesion classificationcited by 4
  11. 2022Vanilla Feedforward Neural Networks as a Discretization of Dynamical Systemscited by 4
  12. 2024Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learningcited by 4
27 more
  1. 2021Comparative evaluation of CNN architectures for Image Caption Generationcited by 3
  2. 2021Rethinking ResNets: Improved Stacking Strategies With High Order Schemescited by 3
  3. 2021m-RevNet: Deep Reversible Neural Networks with Momentumcited by 3
  4. 2022Towards Robust Face Recognition with Comprehensive Searchcited by 3
  5. 2023Certified Invertibility in Neural Networks via Mixed-Integer Programmingcited by 3
  6. 2023A Minimal Control Family of Dynamical Systems for Universal Approximationcited by 3
  7. 2025IM-BERT: Enhancing Robustness of BERT through the Implicit Euler Methodcited by 3
  8. 2021Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Spacecited by 2
  9. 2021Interflow: Aggregating Multi-layer Feature Mappings with Attention Mechanismcited by 2
  10. 2021Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directionscited by 2
  11. 2022FAS-UNet: A Novel FAS-driven Unet to Learn Variational Image Segmentationcited by 2
  12. 2024Convection-Diffusion Equation: A Theoretically Certified Framework for Neural Networkscited by 2
  13. 2025Deep Neural Networks Inspired by Differential Equationscited by 2
  14. 2021Meta-Solver for Neural Ordinary Differential Equationscited by 1
  15. 2022Zero Stability Well Predicts Performance of Convolutional Neural Networkscited by 1
  16. 2023Feature representations useful for predicting image memorabilitycited by 1
  17. 2023SAR-to-Optical Image Translation via Thermodynamics-inspired Networkcited by 1
  18. 2025PMNO: A novel physics guided multi-step neural operator predictor for partial differential equationscited by 1
  19. 2025ODP-Bench: Benchmarking Out-of-Distribution Performance Predictioncited by 1
  20. 2026Understanding the Theoretical Foundations of Deep Neural Networks through Differential Equationscited by 1
  21. 2021Differentiable Neural Architecture Learning for Efficient Neural Network Designcited by 0
  22. 2021Rethinking the constraints of multimodal fusion: case study in Weakly-Supervised Audio-Visual Video Parsingcited by 0
  23. 2021Context-aware PolyUNet for Liver and Lesion Segmentation from Abdominal CT Imagescited by 0
  24. 2024A Novel Method for Accurate & Real-time Food Classification: The Synergistic Integration of EfficientNetB7, CBAM, Transfer Learning, and Data Augmentationcited by 0
  25. 2025Cross-Domain Few-Shot Segmentation via Ordinary Differential Equations over Time Intervalscited by 0
  26. 2025IIET: Efficient Numerical Transformer via Implicit Iterative Euler Methodcited by 0
  27. 2026Deep learning from a control vantage pointcited by 0