On Domain-Specific Pre-Training for Effective Semantic Perception in Agricultural Robotics

• URL: http://arxiv.org/abs/2303.12499v1
• Date: Wed, 22 Mar 2023 12:10:44 GMT
• Title: On Domain-Specific Pre-Training for Effective Semantic Perception in Agricultural Robotics
• Authors: Gianmarco Roggiolani, Federico Magistri, Tiziano Guadagnino, Jan Weyler, Giorgio Grisetti, Cyrill Stachniss, Jens Behley
• Abstract summary: Agricultural robots aim to monitor fields and assess the plants as well as their growth stage in an automatic manner. Semantic perception mostly relies on deep learning using supervised approaches. In this paper, we look into the problem of reducing the amount of labels without compromising the final segmentation performance.
• Score: 30.966137924072097
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agricultural robots have the prospect to enable more efficient and sustainable agricultural production of food, feed, and fiber. Perception of crops and weeds is a central component of agricultural robots that aim to monitor fields and assess the plants as well as their growth stage in an automatic manner. Semantic perception mostly relies on deep learning using supervised approaches, which require time and qualified workers to label fairly large amounts of data. In this paper, we look into the problem of reducing the amount of labels without compromising the final segmentation performance. For robots operating in the field, pre-training networks in a supervised way is already a popular method to reduce the number of required labeled images. We investigate the possibility of pre-training in a self-supervised fashion using data from the target domain. To better exploit this data, we propose a set of domain-specific augmentation strategies. We evaluate our pre-training on semantic segmentation and leaf instance segmentation, two important tasks in our domain. The experimental results suggest that pre-training with domain-specific data paired with our data augmentation strategy leads to superior performance compared to commonly used pre-trainings. Furthermore, the pre-trained networks obtain similar performance to the fully supervised with less labeled data.

Related papers

• Semi-Supervised Active Learning for Semantic Segmentation in Unknown Environments Using Informative Path Planning [27.460481202195012]
  Self-supervised and fully supervised active learning methods emerged to improve a robot's vision. We propose a planning method for semi-supervised active learning of semantic segmentation. We leverage an adaptive map-based planner guided towards the frontiers of unexplored space with high model uncertainty.
  arXiv  Detail & Related papers  (2023-12-07T16:16:47Z)
• Data-Centric Digital Agriculture: A Perspective [23.566985362242498]
  Digital agriculture is rapidly evolving to meet increasing global demand for food, feed, fiber, and fuel. Machine learning research in digital agriculture has predominantly focused on model-centric approaches. To fully realize the potential of digital agriculture, it is crucial to have a comprehensive understanding of the role of data in the field.
  arXiv  Detail & Related papers  (2023-12-06T11:38:26Z)
• In-Domain Self-Supervised Learning Improves Remote Sensing Image Scene Classification [5.323049242720532]
  Self-supervised learning has emerged as a promising approach for remote sensing image classification. We present a study of different self-supervised pre-training strategies and evaluate their effect across 14 downstream datasets.
  arXiv  Detail & Related papers  (2023-07-04T10:57:52Z)
• Productive Crop Field Detection: A New Dataset and Deep Learning Benchmark Results [1.2233362977312945]
  In precision agriculture, detecting productive crop fields is an essential practice that allows the farmer to evaluate operating performance. Previous studies explore different methods to detect crop fields using advanced machine learning algorithms. We propose a high-quality dataset generated by machine operation combined with Sentinel-2 images.
  arXiv  Detail & Related papers  (2023-05-19T20:30:59Z)
• Prior Knowledge-Guided Attention in Self-Supervised Vision Transformers [79.60022233109397]
  We present spatial prior attention (SPAN), a framework that takes advantage of consistent spatial and semantic structure in unlabeled image datasets. SPAN operates by regularizing attention masks from separate transformer heads to follow various priors over semantic regions. We find that the resulting attention masks are more interpretable than those derived from domain-agnostic pretraining.
  arXiv  Detail & Related papers  (2022-09-07T02:30:36Z)
• TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition [77.77786072373942]
  This paper proposes a Transferable Neighborhood Discovery (TraND) framework to bridge the domain gap for unsupervised cross-domain gait recognition. We design an end-to-end trainable approach to automatically discover the confident neighborhoods of unlabeled samples in the latent space. Our method achieves state-of-the-art results on two public datasets, i.e., CASIA-B and OU-LP.
  arXiv  Detail & Related papers  (2021-02-09T03:07:07Z)
• Semi-supervised Gated Recurrent Neural Networks for Robotic Terrain Classification [4.703075836560585]
  We show how highly capable machine learning techniques, namely gated recurrent neural networks, allow our target legged robot to correctly classify the terrain it traverses. We show how raw unlabelled data is used to improve significantly the classification results in a semi-supervised model.
  arXiv  Detail & Related papers  (2020-11-24T06:25:19Z)
• DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks [88.62288327934499]
  We propose a novel augmentation method with language models trained on the linearized labeled sentences. Our method is applicable to both supervised and semi-supervised settings.
  arXiv  Detail & Related papers  (2020-11-03T07:49:15Z)
• Self-training Improves Pre-training for Natural Language Understanding [63.78927366363178]
  We study self-training as another way to leverage unlabeled data through semi-supervised learning. We introduce SentAugment, a data augmentation method which computes task-specific query embeddings from labeled data. Our approach leads to scalable and effective self-training with improvements of up to 2.6% on standard text classification benchmarks.
  arXiv  Detail & Related papers  (2020-10-05T17:52:25Z)
• Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
  We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training. We experimentally verify that the new dataset can significantly improve the ability of the learned FER model. To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
  arXiv  Detail & Related papers  (2020-05-18T09:36:51Z)
• Improving Semantic Segmentation via Self-Training [75.07114899941095]
  We show that we can obtain state-of-the-art results using a semi-supervised approach, specifically a self-training paradigm. We first train a teacher model on labeled data, and then generate pseudo labels on a large set of unlabeled data. Our robust training framework can digest human-annotated and pseudo labels jointly and achieve top performances on Cityscapes, CamVid and KITTI datasets.
  arXiv  Detail & Related papers  (2020-04-30T17:09:17Z)

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.