mlsanityData to 7 Oct 2026

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

arXiv 2105.14693 ↗First posted 31 May 2021cs.CV cs.LGcited by 2

Not on the map. Why?

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 28 of its 45 references that are in the map. First posted on arXiv 31 May 2021.

Builds on

28 of 45 references.

References · 28

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  3. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  4. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  5. 2019Objects as Pointscited by 1,172
  6. 2018Experience Replay for Continual Learningcited by 1,074
  7. 2017Functional Map of the Worldcited by 338
  8. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 287
  9. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  10. 2017Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detectioncited by 209
  11. 2018The Unmanned Aerial Vehicle Benchmark: Object Detection and Trackingcited by 207
  12. 2017Controllable Invariance through Adversarial Feature Learningcited by 127
16 more
  1. 2019A Robust Learning Approach to Domain Adaptive Object Detectioncited by 109
  2. 2020Cross-domain Detection via Graph-induced Prototype Alignmentcited by 109
  3. 2018Modeling Visual Context is Key to Augmenting Object Detection Datasetscited by 106
  4. 2020Continuously Indexed Domain Adaptationcited by 74
  5. 2018The Unusual Effectiveness of Averaging in GAN Trainingcited by 73
  6. 2019Learning to Generate Synthetic Data via Compositingcited by 52
  7. 2018Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Studycited by 48
  8. 2019SpaceNet MVOI: a Multi-View Overhead Imagery Datasetcited by 29
  9. 2020StandardGAN: Multi-source Domain Adaptation for Semantic Segmentation of Very High Resolution Satellite Images by Data Standardizationcited by 23
  10. 2019Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approachcited by 22
  11. 2019Invariant Representations through Adversarial Forgettingcited by 20
  12. 2018Adversarial Examples in Remote Sensingcited by 19
  13. 2019Calibrated Domain-Invariant Learning for Highly Generalizable Large Scale Re-Identificationcited by 14
  14. 2017ME R-CNN: Multi-Expert R-CNN for Object Detectioncited by 13
  15. 2020DAugNet: Unsupervised, Multi-source, Multi-target, and Life-long Domain Adaptation for Semantic Segmentation of Satellite Imagescited by 13
  16. 2014Learning unbiased featurescited by 10

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2025Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Imagescited by 1
  2. 2024LEAP:D -- A Novel Prompt-based Approach for Domain-Generalized Aerial Object Detectioncited by 0