mlsanityData to 7 Oct 2026

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

arXiv 1602.07261 ↗First posted 23 Feb 2016cs.CVcited by 1,509

Not on the map. Why?

Cited by 26 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Very deep convolutional networks have been central to the largest advances in image recognition performance in recent years. One example is the Inception architecture that has been shown to achieve very good performance at relatively low computational cost. Recently, the introduction of residual connections in conjunction with a more traditional architecture has yielded state-of-the-art performance in the 2015 ILSVRC challenge; its performance was similar to the latest generation Inception-v3 network. This raises the question of whether there are any benefit in combining the Inception architecture with residual connections. Here we give clear empirical evidence that training with residual connections accelerates the training of Inception networks significantly. There is also some evidence of residual Inception networks outperforming similarly expensive Inception networks without residual connections by a thin margin. We also present several new streamlined architectures for both residual and non-residual Inception networks. These variations improve the single-frame recognition performance on the ILSVRC 2012 classification task significantly. We further demonstrate how proper activation scaling stabilizes the training of very wide residual Inception networks. With an ensemble of three residual and one Inception-v4, we achieve 3.08 percent top-5 error on the test set of the ImageNet classification (CLS) challenge

Key facts. Cited by 1,509 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Feb 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2017: 1; 2018: 0; 2019: 2; 2020: 1; 2021: 450; 2022: 337; 2023: 315; 2024: 203; 2025: 146; 2026: 54.

1,509 papers.

Sort:

By area:

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  3. 2021RegionCLIP: Region-based Language-Image Pretrainingcited by 612
  4. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  5. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
  6. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  7. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  8. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 359
  9. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 351
  10. 2023InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuningcited by 343
  11. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
  12. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
38 more
  1. 2021DocFormer: End-to-End Transformer for Document Understandingcited by 254
  2. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
  3. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  4. 2023TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessmentcited by 220
  5. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  6. 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 188
  7. 2022mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connectionscited by 185
  8. 2022FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Samplingcited by 179
  9. 2023AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into Onecited by 165
  10. 2021Conformer: Local Features Coupling Global Representations for Visual Recognitioncited by 164
  11. 2021VOLO: Vision Outlooker for Visual Recognitioncited by 164
  12. 2021SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioningcited by 161
  13. 2021Admix: Enhancing the Transferability of Adversarial Attackscited by 155
  14. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  15. 2023mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Videocited by 154
  16. 2023Large-scale Multi-Modal Pre-trained Models: A Comprehensive Surveycited by 153
  17. 2021Well-tuned Simple Nets Excel on Tabular Datasetscited by 151
  18. 2024EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mambacited by 146
  19. 2022More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsitycited by 142
  20. 2023TriDet: Temporal Action Detection with Relative Boundary Modelingcited by 141
  21. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
  22. 2021TransFG: A Transformer Architecture for Fine-grained Recognitioncited by 131
  23. 2022Frequency Domain Model Augmentation for Adversarial Attackcited by 128
  24. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  25. 2021Feature Importance-aware Transferable Adversarial Attackscited by 125
  26. 2021MPViT: Multi-Path Vision Transformer for Dense Predictioncited by 122
  27. 2022ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyondcited by 117
  28. 2022Jury Learning: Integrating Dissenting Voices into Machine Learning Modelscited by 115
  29. 2023A Comprehensive Survey of Dataset Distillationcited by 114
  30. 2021Dive into Deep Learningcited by 111
  31. 2022LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understandingcited by 107
  32. 2021Distilling Object Detectors via Decoupled Featurescited by 105
  33. 2021RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Contentcited by 100
  34. 2022Inception Transformercited by 99
  35. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
  36. 2021CAT: Cross Attention in Vision Transformercited by 92
  37. 2022Improving Adversarial Transferability via Neuron Attribution-Based Attackscited by 92
  38. 2021StructuralLM: Structural Pre-training for Form Understandingcited by 91

50 most cited of 1,509 All 1,509 (JSON)