# Training Domain-invariant Object Detector Faster with Feature Replay and Slow Learner

arXiv: https://arxiv.org/abs/2105.14693 · HTML: https://mlsanity.com/paper/2105.14693/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 31 May 2021.

## Builds on (most cited first, 28 of 28)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Functional Map of the World](https://mlsanity.com/paper/1711.07846/) (2017)
- [Learning from Simulated and Unsupervised Images through Adversarial Training](https://mlsanity.com/paper/1612.07828/) (2016)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking](https://mlsanity.com/paper/1804.00518/) (2018)
- [Controllable Invariance through Adversarial Feature Learning](https://mlsanity.com/paper/1705.11122/) (2017)
- [A Robust Learning Approach to Domain Adaptive Object Detection](https://mlsanity.com/paper/1904.02361/) (2019)
- [Cross-domain Detection via Graph-induced Prototype Alignment](https://mlsanity.com/paper/2003.12849/) (2020)
- [Modeling Visual Context is Key to Augmenting Object Detection Datasets](https://mlsanity.com/paper/1807.07428/) (2018)
- [Continuously Indexed Domain Adaptation](https://mlsanity.com/paper/2007.01807/) (2020)
- [The Unusual Effectiveness of Averaging in GAN Training](https://mlsanity.com/paper/1806.04498/) (2018)
- [Learning to Generate Synthetic Data via Compositing](https://mlsanity.com/paper/1904.05475/) (2019)
- [Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study](https://mlsanity.com/paper/1807.08379/) (2018)
- [SpaceNet MVOI: a Multi-View Overhead Imagery Dataset](https://mlsanity.com/paper/1903.12239/) (2019)
- [Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach](https://mlsanity.com/paper/1908.03856/) (2019)
- [StandardGAN: Multi-source Domain Adaptation for Semantic Segmentation of Very High Resolution Satellite Images by Data Standardization](https://mlsanity.com/paper/2004.06402/) (2020)
- [Invariant Representations through Adversarial Forgetting](https://mlsanity.com/paper/1911.04060/) (2019)
- [Adversarial Examples in Remote Sensing](https://mlsanity.com/paper/1805.10997/) (2018)
- [Calibrated Domain-Invariant Learning for Highly Generalizable Large Scale Re-Identification](https://mlsanity.com/paper/1911.11314/) (2019)
- [ME R-CNN: Multi-Expert R-CNN for Object Detection](https://mlsanity.com/paper/1704.01069/) (2017)
- [DAugNet: Unsupervised, Multi-source, Multi-target, and Life-long Domain Adaptation for Semantic Segmentation of Satellite Images](https://mlsanity.com/paper/2005.06216/) (2020)
- [Learning unbiased features](https://mlsanity.com/paper/1412.5244/) (2014)

## Built on by (most cited first, 2 of 2)

- [Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images](https://mlsanity.com/paper/2505.23193/) (2025)
- [LEAP:D -- A Novel Prompt-based Approach for Domain-Generalized Aerial Object Detection](https://mlsanity.com/paper/2411.09180/) (2024)

## Abstract (arXiv)

In deep learning-based object detection on remote sensing domain, nuisance factors, which affect observed variables while not affecting predictor variables, often matters because they cause domain changes. Previously, nuisance disentangled feature transformation (NDFT) was proposed to build domain-invariant feature extractor with with knowledge of nuisance factors. However, NDFT requires enormous time in a training phase, so it has been impractical. In this paper, we introduce our proposed method, A-NDFT, which is an improvement to NDFT. A-NDFT utilizes two acceleration techniques, feature replay and slow learner. Consequently, on a large-scale UAVDT benchmark, it is shown that our framework can reduce the training time of NDFT from 31 hours to 3 hours while still maintaining the performance. The code will be made publicly available online.