# Learning Adversarial Augmentation Policies for Robust Garlic Seedling Detection

arXiv: https://arxiv.org/abs/2606.26828 · HTML: https://mlsanity.com/paper/2606.26828/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 25 Jun 2026.

## Builds on (most cited first, 24 of 24)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [Adversarial AutoAugment](https://mlsanity.com/paper/1912.11188/) (2019)
- [Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions](https://mlsanity.com/paper/2112.08088/) (2021)
- [Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection](https://mlsanity.com/paper/2205.03346/) (2022)
- [Online Hyper-parameter Learning for Auto-Augmentation Strategy](https://mlsanity.com/paper/1905.07373/) (2019)
- [FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision](https://mlsanity.com/paper/2308.03594/) (2023)
- [GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditions](https://mlsanity.com/paper/2209.14922/) (2022)
- [Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2312.01220/) (2023)
- [Learning Instance-Specific Augmentations by Capturing Local Invariances](https://mlsanity.com/paper/2206.00051/) (2022)
- [You Only Look Around: Learning Illumination Invariant Feature for Low-light Object Detection](https://mlsanity.com/paper/2410.18398/) (2024)
- [LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems](https://mlsanity.com/paper/1705.05922/) (2017)
- [AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation](https://mlsanity.com/paper/2306.07197/) (2023)
- [Image-to-Image Translation-based Data Augmentation for Robust EV Charging Inlet Detection](https://mlsanity.com/paper/2112.05290/) (2021)
- [Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label](https://mlsanity.com/paper/2404.09475/) (2024)

## Abstract (arXiv)

Accurate seedling detection during early growth stages is essential for timely replanting and effective crop management in precision agriculture. However, existing studies are mostly evaluated under relatively stable imaging conditions, such as UAV imagery or greenhouse environments, leaving robust detection under severe and spatially heterogeneous illumination in ground-based outdoor monitoring insufficiently explored. In addition, many illumination-robust detection methods rely on additional enhancement or feature-extraction modules, which increase inference-time overhead and are not tailored to seedling detection and downstream missing seedling localization. To address these gaps, we construct a new garlic seedling dataset captured using a ground-based monitoring platform under real outdoor field conditions with highly variable illumination. We further propose an illumination-robust seedling detection framework based on adversarial augmentation policy learning. The proposed method jointly optimizes a stochastic augmentation policy agent and an object detector, enabling the detector to learn robust representations under challenging visual conditions. A structural penalty is introduced to prevent unrealistic distortions while encouraging challenging augmentations during training. Extensive experiments show that the proposed approach achieves an AP50 of 91.6%, improving the baseline by 0.9 percentage points and outperforming the previous best-performing method by 0.2 percentage points. For downstream missing seedling localization, it achieves 75.0% precision and a 67.0% F1-score, improving the baseline by 4.8 and 2.0 percentage points, respectively. These results demonstrate the effectiveness of the proposed framework for practical ground-based agricultural monitoring under complex outdoor lighting conditions without additional inference-time computational overhead.