No article text was recorded for this version.
auxiliary batch normalization
Version 2 of 289 papers144 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Intriguing properties of adversarial training
- Blog: Adversarial Amendment is the Only Force Capable of Transforming an Enemy into a Friend
- Blog: Concurrent Adversarial Learning for Large-Batch Training
- Blog: Robust Pre-Training by Adversarial Contrastive Learning
- Blog: Intriguing Properties of Adversarial Training at Scale
- Blog: Adversarial Examples Improve Image Recognition
- Blog: Fast AdvProp
- Blog: Intriguing properties of adversarial training
- Blog: Adversarial Examples Improve Image Recognition
- Blog: Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples
- Blog: Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition
- Blog: Linearizing Models for Efficient yet Robust Private Inference
- Blog: FLOAT: Fast Learnable Once-for-All Adversarial Training for Tunable Trade-off between Accuracy and Robustness
- Blog: Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free
- Blog: Concurrent Adversarial Learning for Large-Batch Training
- Blog: Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images
- Blog: Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spotting
- Blog: Bag of Tricks for Adversarial Training
- Blog: Robust and Accurate Object Detection via Self-Knowledge Distillation
- Blog: Towards Understanding Dual BN In Hybrid Adversarial Training
- Blog: 3D Point Cloud Completion with Geometric-Aware Adversarial Augmentation
- Blog: Adversarial Learning Under Hybrid Perturbations for Robust Acute Lymphoblastic Leukemia Classification
- Blog: Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition
- Blog: Defending Against Multiple and Unforeseen Adversarial Videos
- Blog: Linearizing Models for Efficient yet Robust Private Inference
- Blog: Adversarial momentum-contrastive pre-training
- Blog: Robust Pre-Training by Adversarial Contrastive Learning
- Blog: OpenCoS: Contrastive Semi-supervised Learning for Handling Open-Set Unlabeled Data
- Blog: Adversarial Amendment is the Only Force Capable of Transforming an Enemy into a Friend
- Blog: Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off
- Blog: Adversarial Contrastive Learning Based Physics-Informed Temporal Networks for Cuffless Blood Pressure Estimation
- Blog: Defending Against Multiple and Unforeseen Adversarial Videos
- Blog: Removing Batch Normalization Boosts Adversarial Training
- Blog: Federated Robustness Propagation: Sharing Adversarial Robustness in Federated Learning
- Blog: Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition
- Blog: Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification
- Blog: Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition
- Blog: Auxiliary Training: Towards Accurate and Robust Models
- Blog: Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free
- Blog: Does Data Augmentation Benefit from Split BatchNorms
- Blog: Revisiting the Trade-off between Accuracy and Robustness via Weight Distribution of Filters
- Blog: Federated Robustness Propagation: Sharing Adversarial Robustness in Heterogeneous Federated Learning
- Blog: TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization
- Blog: Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images
- Blog: Rethinking Adversarial Training with Neural Tangent Kernel
- Blog: Towards Robust Vision Transformer via Masked Adaptive Ensemble
- Blog: Improving Model Generalization by On-manifold Adversarial Augmentation in the Frequency Domain
- Blog: Zero-Sacrifice Persistent-Robustness Adversarial Defense for Pre-Trained Encoders
- Blog: A Low-Rank Defense Method for Adversarial Attack on Diffusion Models
- Blog: Encoding Robustness to Image Style via Adversarial Feature Perturbations
- Blog: DetectX - Adversarial Input Detection using Current Signatures in Memristive XBar Arrays
- Blog: Improve Video Representation with Temporal Adversarial Augmentation
- Blog: Removing Batch Normalization Boosts Adversarial Training
- Blog: Large Norms of CNN Layers Do Not Hurt Adversarial Robustness
- Blog: Self-Supervised Adversarial Training via Diverse Augmented Queries and Self-Supervised Double Perturbation
- Blog: Fourier-Basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification
- Blog: A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness
- Blog: Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective
- Blog: TaiChi: Improving the Robustness of NLP Models by Seeking Common Ground While Reserving Differences
- Blog: Splitting the Difference on Adversarial Training
Showing 60 of 89 papers.
History & citation
Current · Permanent link
- Decoupling Batch Statistics for Robust Deep Learning merged into this direction (55% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_auxiliary_batch_normalization_05f7efdf,
title = {auxiliary batch normalization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/auxiliary-batch-normalization/rdr_05f7efdf889d4a71add9cdc0b15f750a},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_auxiliary_batch_normalization_05f7efdf_v2,
title = {auxiliary batch normalization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/auxiliary-batch-normalization/rdr_05f7efdf889d4a71add9cdc0b15f750a/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}