# Transfer Learning from Synthetic In-vitro Soybean Pods Dataset for In-situ Segmentation of On-branch Soybean Pod

arXiv: https://arxiv.org/abs/2204.10902 · HTML: https://mlsanity.com/paper/2204.10902/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 35 references that are in the map.
- First posted on arXiv 22 Apr 2022.

## Builds on (most cited first, 12 of 12)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [YOLACT: Real-time Instance Segmentation](https://mlsanity.com/paper/1904.02689/) (2019)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [Deep learning in agriculture: A survey](https://mlsanity.com/paper/1807.11809/) (2018)
- [BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation](https://mlsanity.com/paper/2001.00309/) (2020)
- [Counting of Grapevine Berries in Images via Semantic Segmentation using Convolutional Neural Networks](https://mlsanity.com/paper/2004.14010/) (2020)
- [Active Learning with Point Supervision for Cost-Effective Panicle Detection in Cereal Crops](https://mlsanity.com/paper/1910.01789/) (2019)
- [Data Augmentation for Leaf Segmentation and Counting Tasks in Rosette Plants](https://mlsanity.com/paper/1903.08583/) (2019)
- [Automatic estimation of heading date of paddy rice using deep learning](https://mlsanity.com/paper/1906.07917/) (2019)
- [High Throughput Soybean Pod-Counting with In-Field Robotic Data Collection and Machine-Vision Based Data Analysis](https://mlsanity.com/paper/2105.10568/) (2021)

## Built on by (most cited first, 2 of 2)

- [The Power of Transfer Learning in Agricultural Applications: AgriNet](https://mlsanity.com/paper/2207.03881/) (2022)
- [CongNaMul: A Dataset for Advanced Image Processing of Soybean Sprouts](https://mlsanity.com/paper/2308.15690/) (2023)

## Abstract (arXiv)

The mature soybean plants are of complex architecture with pods frequently touching each other, posing a challenge for in-situ segmentation of on-branch soybean pods. Deep learning-based methods can achieve accurate training and strong generalization capabilities, but it demands massive labeled data, which is often a limitation, especially for agricultural applications. As lacking the labeled data to train an in-situ segmentation model for on-branch soybean pods, we propose a transfer learning from synthetic in-vitro soybean pods. First, we present a novel automated image generation method to rapidly generate a synthetic in-vitro soybean pods dataset with plenty of annotated samples. The in-vitro soybean pods samples are overlapped to simulate the frequently physically touching of on-branch soybean pods. Then, we design a two-step transfer learning. In the first step, we finetune an instance segmentation network pretrained by a source domain (MS COCO dataset) with a synthetic target domain (in-vitro soybean pods dataset). In the second step, transferring from simulation to reality is performed by finetuning on a few real-world mature soybean plant samples. The experimental results show the effectiveness of the proposed two-step transfer learning method, such that AP50 was 0.80 for the real-world mature soybean plant test dataset, which is higher than that of direct adaptation and its AP50 was 0.77. Furthermore, the visualizations of in-situ segmentation results of on-branch soybean pods show that our method performs better than other methods, especially when soybean pods overlap densely.