# Progressive Transformation Learning for Leveraging Virtual Images in Training

arXiv: https://arxiv.org/abs/2211.01778 · HTML: https://mlsanity.com/paper/2211.01778/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 59 references that are in the map.
- First posted on arXiv 3 Nov 2022.

## Builds on (most cited first, 30 of 37)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [Virtual Worlds as Proxy for Multi-Object Tracking Analysis](https://mlsanity.com/paper/1605.06457/) (2016)
- [YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications](https://mlsanity.com/paper/2209.02976/) (2022)
- [Detection and Tracking Meet Drones Challenge](https://mlsanity.com/paper/2001.06303/) (2020)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [Net2Net: Accelerating Learning via Knowledge Transfer](https://mlsanity.com/paper/1511.05641/) (2015)
- [Video Panoptic Segmentation](https://mlsanity.com/paper/2006.11339/) (2020)
- [SynFace: Face Recognition with Synthetic Data](https://mlsanity.com/paper/2108.07960/) (2021)
- [Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping](https://mlsanity.com/paper/2010.13369/) (2020)
- [Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World](https://mlsanity.com/paper/1803.08319/) (2018)
- [Network Morphism](https://mlsanity.com/paper/1603.01670/) (2016)
- [Learning from Synthetic Animals](https://mlsanity.com/paper/1912.08265/) (2019)
- [From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation](https://mlsanity.com/paper/2103.14843/) (2021)
- [Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection](https://mlsanity.com/paper/1706.03038/) (2017)
- [Label, Verify, Correct: A Simple Few Shot Object Detection Method](https://mlsanity.com/paper/2112.05749/) (2021)
- [Automated Progressive Learning for Efficient Training of Vision Transformers](https://mlsanity.com/paper/2203.14509/) (2022)
- [CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data](https://mlsanity.com/paper/2112.09081/) (2021)

## Built on by (most cited first, 10 of 10)

- [LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living](https://mlsanity.com/paper/2406.09390/) (2024)
- [Diversifying Human Pose in Synthetic Data for Aerial-view Human Detection](https://mlsanity.com/paper/2405.15939/) (2024)
- [TK-Planes: Tiered K-Planes with High Dimensional Feature Vectors for Dynamic UAV-based Scenes](https://mlsanity.com/paper/2405.02762/) (2024)
- [Exploring the Impact of Synthetic Data for Aerial-view Human Detection](https://mlsanity.com/paper/2405.15203/) (2024)
- [Exploring the Potential of Synthetic Data to Replace Real Data](https://mlsanity.com/paper/2408.14559/) (2024)
- [SynPlay: Large-Scale Synthetic Human Data with Real-World Diversity for Aerial-View Perception](https://mlsanity.com/paper/2408.11814/) (2024)
- [UAVTwin: Neural Digital Twins for UAVs using Gaussian Splatting](https://mlsanity.com/paper/2504.02158/) (2025)
- [Visual Prototype Conditioned Focal Region Generation for UAV-Based Object Detection](https://mlsanity.com/paper/2604.02966/) (2026)
- [Coarse-to-Fine Hierarchical Alignment for UAV-based Human Detection using Diffusion Models](https://mlsanity.com/paper/2512.13869/) (2025)
- [Curriculum-Based Strategies for Efficient Cross-Domain Action Recognition](https://mlsanity.com/paper/2601.14101/) (2026)

## Abstract (arXiv)

To effectively interrogate UAV-based images for detecting objects of interest, such as humans, it is essential to acquire large-scale UAV-based datasets that include human instances with various poses captured from widely varying viewing angles. As a viable alternative to laborious and costly data curation, we introduce Progressive Transformation Learning (PTL), which gradually augments a training dataset by adding transformed virtual images with enhanced realism. Generally, a virtual2real transformation generator in the conditional GAN framework suffers from quality degradation when a large domain gap exists between real and virtual images. To deal with the domain gap, PTL takes a novel approach that progressively iterates the following three steps: 1) select a subset from a pool of virtual images according to the domain gap, 2) transform the selected virtual images to enhance realism, and 3) add the transformed virtual images to the training set while removing them from the pool. In PTL, accurately quantifying the domain gap is critical. To do that, we theoretically demonstrate that the feature representation space of a given object detector can be modeled as a multivariate Gaussian distribution from which the Mahalanobis distance between a virtual object and the Gaussian distribution of each object category in the representation space can be readily computed. Experiments show that PTL results in a substantial performance increase over the baseline, especially in the small data and the cross-domain regime.