Learning Adversarial Augmentation Policies for Robust Garlic Seedling Detection

• URL: http://arxiv.org/abs/2606.26828v1
• Date: Thu, 25 Jun 2026 10:08:37 GMT
• Title: Learning Adversarial Augmentation Policies for Robust Garlic Seedling Detection
• Abstract summary: We propose an illumination-robust seedling detection framework based on augmentation policy learning.<n>The proposed approach achieves an AP$_50$ of 91.6%, improving the baseline by 0.9 percentage points.<n>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.
• Score: 9.496377791237425
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 AP$_{50}$ 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.

Related papers

• SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation [71.91583446135651]
  We propose SAFE-Pruner, a plug-and-play pruning framework that incorporates attention cues of future layers into pruning decisions.<n>We show that our method achieves up to 1.89x speedup with a minimal degradation in success rate of less than 1.7%, while outperforming state-of-the-art methods by up to 1.9%.
  arXiv  Detail & Related papers  (2026-05-28T09:23:08Z)
• Uncertainty-Aware Wildfire Smoke Density Classification from Satellite Imagery via CBAM-Augmented EfficientNet with Evidential Deep Learning [0.0]
  We propose a probabilistic framework to categorize a satellite patch into Light, Moderate, and Heavy severity classes.<n>A CBAM module with an evidential deep learning head predicts Dirichlet concentration parameters, directly estimating vacuity (epistemic) and dissonance (aleatoric) without Monte Carlo sampling.<n>Our architecture uses the backbone of a pre-trained EfficientNet-B3 and a CBAM module with an evidential deep learning head that predicts Dirichlet concentration parameters.
  arXiv  Detail & Related papers  (2026-05-15T12:22:38Z)
• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditions [58.37558408672509]
  We propose a robust self-supervised training paradigm, consisting of two key steps: robust self-supervised scene correspondence learning and adverse weather distillation.<n>Experiments demonstrate the effectiveness and versatility of our proposed solution, which outperforms existing state-of-the-art self-supervised methods.
  arXiv  Detail & Related papers  (2025-09-23T15:41:40Z)
• Weed Detection in Challenging Field Conditions: A Semi-Supervised Framework for Overcoming Shadow Bias and Data Scarcity [7.019137213828947]
  This study tackles both issues through a diagnostic-driven, semi-supervised framework.<n>We use a unique dataset of approximately 975 labeled and 10,000 unlabeled images of Guinea Grass in sugarcane.<n>Our work provides a clear and field-tested framework for developing, diagnosing, and improving robust computer vision systems.
  arXiv  Detail & Related papers  (2025-08-27T01:55:47Z)
• Fourier Domain Adaptation for Traffic Light Detection in Adverse Weather [1.1411980034550504]
  Traffic light detection under adverse weather conditions remains largely unexplored in ADAS systems.<n>This paper proposes Fourier Domain Adaptation (FDA), which requires only training data modifications without architectural changes.<n>FDA minimizes the domain gap between source and target domains, creating a dataset for reliable performance under adverse weather.
  arXiv  Detail & Related papers  (2024-11-12T16:15:25Z)
• Manifold Sampling for Differentiable Uncertainty in Radiance Fields [82.17927517146929]
  We propose a versatile approach for learning Gaussian radiance fields with explicit and fine-grained uncertainty estimates. We demonstrate state-of-the-art performance on next-best-view planning tasks.
  arXiv  Detail & Related papers  (2024-09-19T11:22:20Z)
• An Autonomous Drone Swarm for Detecting and Tracking Anomalies among Dense Vegetation [3.6394530599964026]
  We show that swarms of drones can detect and track heavily occluded targets practically feasible. In our real-life field experiments with a swarm of six drones, we achieved an average positional accuracy of 0.39 m with an average precision of 93.2%. We show that sensor noise can effectively be included in the synthetic aperture image integration process.
  arXiv  Detail & Related papers  (2024-07-15T14:31:21Z)
• Enhancing Lidar-based Object Detection in Adverse Weather using Offset Sequences in Time [1.1725016312484975]
  Lidar-based object detection is significantly affected by adverse weather conditions such as rain and fog. Our research provides a comprehensive study of effective methods for mitigating the effects of adverse weather on the reliability of lidar-based object detection.
  arXiv  Detail & Related papers  (2024-01-17T08:31:58Z)
• View Consistent Purification for Accurate Cross-View Localization [59.48131378244399]
  This paper proposes a fine-grained self-localization method for outdoor robotics. The proposed method addresses limitations in existing cross-view localization methods. It is the first sparse visual-only method that enhances perception in dynamic environments.
  arXiv  Detail & Related papers  (2023-08-16T02:51:52Z)
• 6D Camera Relocalization in Visually Ambiguous Extreme Environments [79.68352435957266]
  We propose a novel method to reliably estimate the pose of a camera given a sequence of images acquired in extreme environments such as deep seas or extraterrestrial terrains. Our method achieves comparable performance with state-of-the-art methods on the indoor benchmark (7-Scenes dataset) using only 20% training data.
  arXiv  Detail & Related papers  (2022-07-13T16:40:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.