# Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

arXiv: https://arxiv.org/abs/1807.09441 · HTML: https://mlsanity.com/paper/1807.09441/

## Key facts

- Cited by 364 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2018.

## Built on by (most cited first, 30 of 364)

- [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)
- [HINet: Half Instance Normalization Network for Image Restoration](https://mlsanity.com/paper/2105.06086/) (2021)
- [RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening](https://mlsanity.com/paper/2103.15597/) (2021)
- [FSDR: Frequency Space Domain Randomization for Domain Generalization](https://mlsanity.com/paper/2103.02370/) (2021)
- [Uncertainty Modeling for Out-of-Distribution Generalization](https://mlsanity.com/paper/2202.03958/) (2022)
- [EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization](https://mlsanity.com/paper/2303.01904/) (2023)
- [TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation](https://mlsanity.com/paper/2302.05155/) (2023)
- [Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark](https://mlsanity.com/paper/2311.06750/) (2023)
- [AugMax: Adversarial Composition of Random Augmentations for Robust Training](https://mlsanity.com/paper/2110.13771/) (2021)
- [Cluster Contrast for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.11568/) (2021)
- [Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2204.02548/) (2022)
- [CLIP the Gap: A Single Domain Generalization Approach for Object Detection](https://mlsanity.com/paper/2301.05499/) (2023)
- [Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2312.04265/) (2023)
- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)
- [Semantic-Aware Domain Generalized Segmentation](https://mlsanity.com/paper/2204.00822/) (2022)
- [WildNet: Learning Domain Generalized Semantic Segmentation from the Wild](https://mlsanity.com/paper/2204.01446/) (2022)
- [Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation](https://mlsanity.com/paper/2207.04892/) (2022)
- [ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification](https://mlsanity.com/paper/2103.16364/) (2021)
- [Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes](https://mlsanity.com/paper/2207.11707/) (2022)
- [Body Part-Based Representation Learning for Occluded Person Re-Identification](https://mlsanity.com/paper/2211.03679/) (2022)
- [Unifying Short and Long-Term Tracking with Graph Hierarchies](https://mlsanity.com/paper/2212.03038/) (2022)
- [Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation](https://mlsanity.com/paper/2108.02376/) (2021)
- [Person Re-identification Method Based on Color Attack and Joint Defence](https://mlsanity.com/paper/2111.09571/) (2021)
- [Intra-Inter Camera Similarity for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.11658/) (2021)
- [IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID](https://mlsanity.com/paper/2108.02413/) (2021)
- [Test-time Batch Statistics Calibration for Covariate Shift](https://mlsanity.com/paper/2110.04065/) (2021)
- [Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofing](https://mlsanity.com/paper/2108.02667/) (2021)
- [Pin the Memory: Learning to Generalize Semantic Segmentation](https://mlsanity.com/paper/2204.03609/) (2022)

## Abstract (arXiv)

Convolutional neural networks (CNNs) have achieved great successes in many computer vision problems. Unlike existing works that designed CNN architectures to improve performance on a single task of a single domain and not generalizable, we present IBN-Net, a novel convolutional architecture, which remarkably enhances a CNN's modeling ability on one domain (e.g. Cityscapes) as well as its generalization capacity on another domain (e.g. GTA5) without finetuning. IBN-Net carefully integrates Instance Normalization (IN) and Batch Normalization (BN) as building blocks, and can be wrapped into many advanced deep networks to improve their performances. This work has three key contributions. (1) By delving into IN and BN, we disclose that IN learns features that are invariant to appearance changes, such as colors, styles, and virtuality/reality, while BN is essential for preserving content related information. (2) IBN-Net can be applied to many advanced deep architectures, such as DenseNet, ResNet, ResNeXt, and SENet, and consistently improve their performance without increasing computational cost. (3) When applying the trained networks to new domains, e.g. from GTA5 to Cityscapes, IBN-Net achieves comparable improvements as domain adaptation methods, even without using data from the target domain. With IBN-Net, we won the 1st place on the WAD 2018 Challenge Drivable Area track, with an mIoU of 86.18%.