# Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks

arXiv: https://arxiv.org/abs/1805.07925 · HTML: https://mlsanity.com/paper/1805.07925/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2018.

## Built on by (most cited first, 30 of 78)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation](https://mlsanity.com/paper/2208.05117/) (2022)
- [AugMax: Adversarial Composition of Random Augmentations for Robust Training](https://mlsanity.com/paper/2110.13771/) (2021)
- [NICO++: Towards Better Benchmarking for Domain Generalization](https://mlsanity.com/paper/2204.08040/) (2022)
- [Adversarially Adaptive Normalization for Single Domain Generalization](https://mlsanity.com/paper/2106.01899/) (2021)
- [Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofing](https://mlsanity.com/paper/2108.02667/) (2021)
- [SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization](https://mlsanity.com/paper/2310.19795/) (2023)
- [A Survey on Deep Domain Adaptation for LiDAR Perception](https://mlsanity.com/paper/2106.02377/) (2021)
- [Style Normalization and Restitution for Domain Generalization and Adaptation](https://mlsanity.com/paper/2101.00588/) (2021)
- [Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization](https://mlsanity.com/paper/2108.08596/) (2021)
- [DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation](https://mlsanity.com/paper/2103.13447/) (2021)
- [RobustSAM: Segment Anything Robustly on Degraded Images](https://mlsanity.com/paper/2406.09627/) (2024)
- [Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition](https://mlsanity.com/paper/2110.10101/) (2021)
- [Unsupervised Multi-Source Domain Adaptation for Person Re-Identification](https://mlsanity.com/paper/2104.12961/) (2021)
- [Few-shot Open-set Recognition by Transformation Consistency](https://mlsanity.com/paper/2103.01537/) (2021)
- [Decompose, Adjust, Compose: Effective Normalization by Playing with Frequency for Domain Generalization](https://mlsanity.com/paper/2303.02328/) (2023)
- [Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2403.00567/) (2024)
- [WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation](https://mlsanity.com/paper/2109.14196/) (2021)
- [Single-source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification](https://mlsanity.com/paper/2209.01634/) (2022)
- [Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2407.18568/) (2024)
- [Cross-Domain Ensemble Distillation for Domain Generalization](https://mlsanity.com/paper/2211.14058/) (2022)
- [DomainAdaptor: A Novel Approach to Test-time Adaptation](https://mlsanity.com/paper/2308.10297/) (2023)
- [SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Maps](https://mlsanity.com/paper/2201.05120/) (2022)
- [Few-Shot Adaptation of Pre-Trained Networks for Domain Shift](https://mlsanity.com/paper/2205.15234/) (2022)
- [Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification](https://mlsanity.com/paper/2206.12513/) (2022)
- [Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning](https://mlsanity.com/paper/2306.10511/) (2023)
- [Hierarchical Dynamic Image Harmonization](https://mlsanity.com/paper/2211.08639/) (2022)
- [Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issues](https://mlsanity.com/paper/2303.08106/) (2023)

## Abstract (arXiv)

Real-world image recognition is often challenged by the variability of visual styles including object textures, lighting conditions, filter effects, etc. Although these variations have been deemed to be implicitly handled by more training data and deeper networks, recent advances in image style transfer suggest that it is also possible to explicitly manipulate the style information. Extending this idea to general visual recognition problems, we present Batch-Instance Normalization (BIN) to explicitly normalize unnecessary styles from images. Considering certain style features play an essential role in discriminative tasks, BIN learns to selectively normalize only disturbing styles while preserving useful styles. The proposed normalization module is easily incorporated into existing network architectures such as Residual Networks, and surprisingly improves the recognition performance in various scenarios. Furthermore, experiments verify that BIN effectively adapts to completely different tasks like object classification and style transfer, by controlling the trade-off between preserving and removing style variations. BIN can be implemented with only a few lines of code using popular deep learning frameworks.