% Key papers for Theory of convolutional inductive bias (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2017_variational_36449,
  title = {{Variational Dropout Sparsifies Deep Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/793},
}

@inproceedings{cvpr2017_fc4_12256,
  title = {{FC4: Fully Convolutional Color Constancy With Confidence-Weighted Pooling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2020_on_15975,
  title = {{On Translation Invariance in CNNs: Convolutional Layers Can Exploit Absolute Spatial Location}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2017_all_12053,
  title = {{All You Need Is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks With Orthonormality and Modulation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{aaai2019_cnn_101505,
  title = {{CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4193},
}

@inproceedings{iclr2019_the_29149,
  title = {{The Singular Values of Convolutional Layers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/982},
}

@inproceedings{iclr2017_regularizing_28235,
  title = {{Regularizing CNNs with Locally Constrained Decorrelations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=ByOvsIqeg},
}

@inproceedings{aaai2019_weighted_103462,
  title = {{Weighted Channel Dropout for Regularization of Deep Convolutional Neural Network}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4858},
}

@inproceedings{iclr2021_training_30727,
  title = {{Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3292},
}

@inproceedings{iclr2020_identity_29256,
  title = {{Identity Crisis: Memorization and Generalization Under Extreme Overparameterization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=B1l6y0VFPr},
}

@inproceedings{iclr2017_inductive_28229,
  title = {{Inductive Bias of Deep Convolutional Networks through Pooling Geometry}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=BkVsEMYel},
}

@inproceedings{iclr2020_generalization_29741,
  title = {{Generalization bounds for deep convolutional neural networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=r1e_FpNFDr},
}

@inproceedings{icml2020_decoupled_38083,
  title = {{Decoupled Greedy Learning of CNNs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6264},
}

@inproceedings{neurips2017_invariance_56395,
  title = {{Invariance and Stability of Deep Convolutional Representations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9392},
}

@inproceedings{neurips2019_preventing_58828,
  title = {{Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14435},
}

@inproceedings{neurips2020_kernel_60125,
  title = {{Kernel Based Progressive Distillation for Adder Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16910},
}

@inproceedings{cvpr2018_feature_13109,
  title = {{Feature Quantization for Defending Against Distortion of Images}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Sun_Feature_Quantization_for_CVPR_2018_paper.html},
}

@inproceedings{iclr2020_deep_29887,
  title = {{Deep Audio Priors Emerge From Harmonic Convolutional Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rygjHxrYDB},
}

@inproceedings{cvpr2018_stochastic_13614,
  title = {{Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Kuen_Stochastic_Downsampling_for_CVPR_2018_paper.html},
}

@inproceedings{aaai2017_regularization_104410,
  title = {{Regularization for Unsupervised Deep Neural Nets}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10787},
}

@inproceedings{aaai2024_targeted_7497,
  title = {{Targeted Activation Penalties Help CNNs Ignore Spurious Signals}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29610},
}

@inproceedings{aaai2025_layeract_9714,
  title = {{LayerAct: Advanced Activation Mechanism for Robust Inference of CNNs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34374},
}

@inproceedings{neurips2024_nonparametric_73333,
  title = {{Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94112},
}

@inproceedings{aaai2024_convolutional_5507,
  title = {{Convolutional Spectral Kernel Learning with Generalization Guarantees (Abstract Reprint)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30604},
}

@inproceedings{aaai2025_don_8801,
  title = {{Don’t Think It Twice: Exploit Shift Invariance for Efficient Online Streaming Inference of CNNs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33958},
}

@inproceedings{icml2026_riemannian_50066,
  title = {{Riemannian Networks over Full-Rank Correlation Matrices}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=8k4om4zj5E},
}

@inproceedings{iclr2026_batch_86754,
  title = {{Batch Pruning by Activation Stability}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=TUADW7db5n},
}

@inproceedings{neurips2026_layer_93622,
  title = {{Layer Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/152401},
}