# MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection

arXiv: https://arxiv.org/abs/2309.01086 · HTML: https://mlsanity.com/paper/2309.01086/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 45 references that are in the map.
- First posted on arXiv 3 Sep 2023.

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

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [Unbiased Mean Teacher for Cross-domain Object Detection](https://mlsanity.com/paper/2003.00707/) (2020)
- [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)
- [Harmonizing Transferability and Discriminability for Adapting Object Detectors](https://mlsanity.com/paper/2003.06297/) (2020)
- [Cross-Domain Adaptive Teacher for Object Detection](https://mlsanity.com/paper/2111.13216/) (2021)
- [Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection](https://mlsanity.com/paper/1905.05396/) (2019)
- [Multi-adversarial Faster-RCNN for Unrestricted Object Detection](https://mlsanity.com/paper/1907.10343/) (2019)
- [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)
- [MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2103.04224/) (2021)
- [Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation](https://mlsanity.com/paper/2003.10275/) (2020)
- [Learning Dynamic Memory Networks for Object Tracking](https://mlsanity.com/paper/1803.07268/) (2018)
- [Spatial Attention Pyramid Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2003.12979/) (2020)
- [Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN](https://mlsanity.com/paper/2007.01571/) (2020)
- [Adapting Object Detectors with Conditional Domain Normalization](https://mlsanity.com/paper/2003.07071/) (2020)
- [Domain Adaptation for Object Detection via Style Consistency](https://mlsanity.com/paper/1911.10033/) (2019)
- [Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection](https://mlsanity.com/paper/2110.01428/) (2021)
- [Decoupled Adaptation for Cross-Domain Object Detection](https://mlsanity.com/paper/2110.02578/) (2021)
- [SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses](https://mlsanity.com/paper/1911.02559/) (2019)
- [iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection](https://mlsanity.com/paper/2003.04132/) (2020)
- [Multi-level Domain Adaptive learning for Cross-Domain Detection](https://mlsanity.com/paper/1907.11484/) (2019)

## Built on by (most cited first, 7 of 7)

- [CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection](https://mlsanity.com/paper/2403.19278/) (2024)
- [Universal Domain Adaptive Object Detection via Dual Probabilistic Alignment](https://mlsanity.com/paper/2412.11443/) (2024)
- [Single-Domain Generalized Object Detection by Balancing Domain Diversity and Invariance](https://mlsanity.com/paper/2502.03835/) (2025)
- [Visually Similar Pair Alignment for Robust Cross-Domain Object Detection](https://mlsanity.com/paper/2504.06607/) (2025)
- [Domain Adaptive Object Detection via Dual-Stream Bilevel-Cycle Optimization](https://mlsanity.com/paper/2606.31373/) (2026)
- [CLDA-YOLO: Visual Contrastive Learning Based Domain Adaptive YOLO Detector](https://mlsanity.com/paper/2412.11812/) (2024)
- [Domain Adaptive Object Detection for Space Applications with Real-Time Constraints](https://mlsanity.com/paper/2509.17593/) (2025)

## Abstract (arXiv)

Cross-domain object detection is challenging, and it involves aligning labeled source and unlabeled target domains. Previous approaches have used adversarial training to align features at both image-level and instance-level. At the instance level, finding a suitable source sample that aligns with a target sample is crucial. A source sample is considered suitable if it differs from the target sample only in domain, without differences in unimportant characteristics such as orientation and color, which can hinder the model's focus on aligning the domain difference. However, existing instance-level feature alignment methods struggle to find suitable source instances because their search scope is limited to mini-batches. Mini-batches are often so small in size that they do not always contain suitable source instances. The insufficient diversity of mini-batches becomes problematic particularly when the target instances have high intra-class variance. To address this issue, we propose a memory-based instance-level domain adaptation framework. Our method aligns a target instance with the most similar source instance of the same category retrieved from a memory storage. Specifically, we introduce a memory module that dynamically stores the pooled features of all labeled source instances, categorized by their labels. Additionally, we introduce a simple yet effective memory retrieval module that retrieves a set of matching memory slots for target instances. Our experiments on various domain shift scenarios demonstrate that our approach outperforms existing non-memory-based methods significantly.