# Deep Domain Confusion: Maximizing for Domain Invariance

arXiv: https://arxiv.org/abs/1412.3474 · HTML: https://mlsanity.com/paper/1412.3474/

## Key facts

- Cited by 602 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2014.

## Built on by (most cited first, 30 of 602)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2110.08733/) (2021)
- [Contrastive Test-Time Adaptation](https://mlsanity.com/paper/2204.10377/) (2022)
- [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022)
- [Improving Out-of-Distribution Robustness via Selective Augmentation](https://mlsanity.com/paper/2201.00299/) (2022)
- [Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization](https://mlsanity.com/paper/2109.02934/) (2021)
- [Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models](https://mlsanity.com/paper/1911.03393/) (2019)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06165/) (2021)
- [Domain Adaptation via Prompt Learning](https://mlsanity.com/paper/2202.06687/) (2022)
- [Deep Subdomain Adaptation Network for Image Classification](https://mlsanity.com/paper/2106.09388/) (2021)
- [Causality-inspired Single-source Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2111.12525/) (2021)
- [Predicting with Confidence on Unseen Distributions](https://mlsanity.com/paper/2107.03315/) (2021)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation](https://mlsanity.com/paper/2106.04732/) (2021)
- [Test-Time Adaptation via Conjugate Pseudo-labels](https://mlsanity.com/paper/2207.09640/) (2022)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Progressive Domain Expansion Network for Single Domain Generalization](https://mlsanity.com/paper/2103.16050/) (2021)
- [Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation](https://mlsanity.com/paper/2205.04183/) (2022)
- [Domain Impression: A Source Data Free Domain Adaptation Method](https://mlsanity.com/paper/2102.09003/) (2021)
- [Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time](https://mlsanity.com/paper/2211.14238/) (2022)
- [Understanding and Improving Visual Prompting: A Label-Mapping Perspective](https://mlsanity.com/paper/2211.11635/) (2022)
- [Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.16765/) (2021)
- [OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping](https://mlsanity.com/paper/2210.10732/) (2022)
- [TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2108.05988/) (2021)
- [Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests](https://mlsanity.com/paper/2106.00545/) (2021)
- [Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation](https://mlsanity.com/paper/2107.05399/) (2021)
- [Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.08566/) (2023)

## Abstract (arXiv)

Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias on a standard benchmark. Fine-tuning deep models in a new domain can require a significant amount of data, which for many applications is simply not available. We propose a new CNN architecture which introduces an adaptation layer and an additional domain confusion loss, to learn a representation that is both semantically meaningful and domain invariant. We additionally show that a domain confusion metric can be used for model selection to determine the dimension of an adaptation layer and the best position for the layer in the CNN architecture. Our proposed adaptation method offers empirical performance which exceeds previously published results on a standard benchmark visual domain adaptation task.