# Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domains

arXiv: https://arxiv.org/abs/2304.02950 · HTML: https://mlsanity.com/paper/2304.02950/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 55 references that are in the map.
- First posted on arXiv 6 Apr 2023.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [A Fourier-based Framework for Domain Generalization](https://mlsanity.com/paper/2105.11120/) (2021)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Generalizing Across Domains via Cross-Gradient Training](https://mlsanity.com/paper/1804.10745/) (2018)
- [Deep Domain-Adversarial Image Generation for Domain Generalisation](https://mlsanity.com/paper/2003.06054/) (2020)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [FSDR: Frequency Space Domain Randomization for Domain Generalization](https://mlsanity.com/paper/2103.02370/) (2021)
- [Exploring Object Relation in Mean Teacher for Cross-Domain Detection](https://mlsanity.com/paper/1904.11245/) (2019)
- [Exploring Categorical Regularization for Domain Adaptive Object Detection](https://mlsanity.com/paper/2003.09152/) (2020)
- [Invariant Rationalization](https://mlsanity.com/paper/2003.09772/) (2020)
- [Cross-domain Detection via Graph-induced Prototype Alignment](https://mlsanity.com/paper/2003.12849/) (2020)
- [Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector](https://mlsanity.com/paper/2008.08574/) (2020)
- [Heterogeneous Risk Minimization](https://mlsanity.com/paper/2105.03818/) (2021)
- [Towards Universal Object Detection by Domain Attention](https://mlsanity.com/paper/1904.04402/) (2019)

## Built on by (most cited first, 24 of 24)

- [Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection](https://mlsanity.com/paper/2405.15225/) (2024)
- [Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives](https://mlsanity.com/paper/2308.01265/) (2023)
- [Fine-grained Recognition with Learnable Semantic Data Augmentation](https://mlsanity.com/paper/2309.00399/) (2023)
- [Causal reasoning in typical computer vision tasks](https://mlsanity.com/paper/2307.13992/) (2023)
- [Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection](https://mlsanity.com/paper/2503.23220/) (2025)
- [Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection](https://mlsanity.com/paper/2503.02101/) (2025)
- [Style-Adaptive Detection Transformer for Single-Source Domain Generalized Object Detection](https://mlsanity.com/paper/2504.20498/) (2025)
- [Causality-Driven Audits of Model Robustness](https://mlsanity.com/paper/2410.23494/) (2024)
- [Single-Domain Generalized Object Detection by Balancing Domain Diversity and Invariance](https://mlsanity.com/paper/2502.03835/) (2025)
- [Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability](https://mlsanity.com/paper/2506.21042/) (2025)
- [Causal-Tune: Mining Causal Factors from Vision Foundation Models for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2512.16567/) (2025)
- [Reducing Spurious Correlation for Federated Domain Generalization](https://mlsanity.com/paper/2407.19174/) (2024)
- [CVGL: Causal Learning and Geometric Topology](https://mlsanity.com/paper/2603.12551/) (2026)
- [RT-SDGOD: Real-Time Single-Domain Generalized Object Detection](https://mlsanity.com/paper/2606.09367/) (2026)
- [Two-Stage Adaptive Network for Semi-Supervised Cross-Domain Crater Detection under Varying Scenario Distributions](https://mlsanity.com/paper/2312.06169/) (2023)
- [Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detection](https://mlsanity.com/paper/2401.05401/) (2023)
- [Hyperspectral Image Cross-Domain Object Detection Method based on Spectral-Spatial Feature Alignment](https://mlsanity.com/paper/2411.16772/) (2024)
- [Mitigating Context Bias in Domain Adaptation for Object Detection using Mask Pooling](https://mlsanity.com/paper/2505.18446/) (2025)
- [Implicit Non-Causal Factors are Out via Dataset Splitting for Domain Generalization Object Detection](https://mlsanity.com/paper/2601.19127/) (2026)
- [Instance-Free Domain Adaptive Object Detection](https://mlsanity.com/paper/2602.06484/) (2026)
- [RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations](https://mlsanity.com/paper/2602.22013/) (2026)
- [VFM4SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detection](https://mlsanity.com/paper/2604.21502/) (2026)
- [Bridge: Basis-Driven Causal Inference Marries VFMs for Domain Generalization](https://mlsanity.com/paper/2604.26820/) (2026)
- [ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification](https://mlsanity.com/paper/2606.09360/) (2026)

## Abstract (arXiv)

Domain shift degrades the performance of object detection models in practical applications. To alleviate the influence of domain shift, plenty of previous work try to decouple and learn the domain-invariant (common) features from source domains via domain adversarial learning (DAL). However, inspired by causal mechanisms, we find that previous methods ignore the implicit insignificant non-causal factors hidden in the common features. This is mainly due to the single-view nature of DAL. In this work, we present an idea to remove non-causal factors from common features by multi-view adversarial training on source domains, because we observe that such insignificant non-causal factors may still be significant in other latent spaces (views) due to the multi-mode structure of data. To summarize, we propose a Multi-view Adversarial Discriminator (MAD) based domain generalization model, consisting of a Spurious Correlations Generator (SCG) that increases the diversity of source domain by random augmentation and a Multi-View Domain Classifier (MVDC) that maps features to multiple latent spaces, such that the non-causal factors are removed and the domain-invariant features are purified. Extensive experiments on six benchmarks show our MAD obtains state-of-the-art performance.