# Task-Relevant and Irrelevant Region-Aware Augmentation for Generalizable Vision-Based Imitation Learning in Agricultural Manipulation

arXiv: https://arxiv.org/abs/2603.04845 · HTML: https://mlsanity.com/paper/2603.04845/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 14 of its 17 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [Scaling Robot Learning with Semantically Imagined Experience](https://mlsanity.com/paper/2302.11550/) (2023)
- [PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures](https://mlsanity.com/paper/2112.05135/) (2021)
- [Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task](https://mlsanity.com/paper/1707.02267/) (2017)
- [XMem++: Production-level Video Segmentation From Few Annotated Frames](https://mlsanity.com/paper/2307.15958/) (2023)
- [RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generation](https://mlsanity.com/paper/2503.18738/) (2025)
- [Semantically Controllable Augmentations for Generalizable Robot Learning](https://mlsanity.com/paper/2409.00951/) (2024)
- [Robust Imitation Learning for Mobile Manipulator Focusing on Task-Related Viewpoints and Regions](https://mlsanity.com/paper/2410.01292/) (2024)

## Built on by (most cited first, 1 of 1)

- [What Matters, When? Diagnosing and Improving Conditional Visual Grounding in Visuomotor Imitation Policies](https://mlsanity.com/paper/2609.05376/) (2026)

## Abstract (arXiv)

Vision-based imitation learning has shown promise for robotic manipulation; however, its generalization remains limited in practical agricultural tasks. This limitation stems from scarce demonstration data and substantial visual domain gaps caused by i) crop-specific appearance diversity and ii) background variations. To address this limitation, we propose Dual-Region Augmentation for Imitation Learning (DRAIL), a region-aware augmentation framework designed for generalizable vision-based imitation learning in agricultural manipulation. DRAIL explicitly separates visual observations into task-relevant and task-irrelevant regions. The task-relevant region is augmented in a domain-knowledge-driven manner to preserve essential visual characteristics, while the task-irrelevant region is aggressively randomized to suppress spurious background correlations. By jointly handling both sources of visual variation, DRAIL promotes learning policies that rely on task-essential features rather than incidental visual cues. We evaluate DRAIL on diffusion policy-based visuomotor controllers through robot experiments on artificial vegetable harvesting and real lettuce defective leaf picking preparation tasks. The results show consistent improvements in success rates under unseen visual conditions compared to baseline methods. Further attention analysis and representation generalization metrics indicate that the learned policies rely more on task-essential visual features, resulting in enhanced robustness and generalization.