Active learning for efficient annotation in precision agriculture: a use-case on crop-weed semantic segmentation

no code implementations • 3 Apr 2024 • Bart M. van Marrewijk, Charbel Dandjinou, Dan Jeric Arcega Rustia, Nicolas Franco Gonzalez, Boubacar Diallo, Jérôme Dias, Paul Melki, Pieter M. Blok

Our results indicated that active learning, especially PowerBALD, yields a higher performance than Random sampling on both datasets.

Active Learning Semantic Segmentation

DODA: Diffusion for Object-detection Domain Adaptation in Agriculture

1 code implementation • 27 Mar 2024 • Shuai Xiang, Pieter M. Blok, James Burridge, Haozhou Wang, Wei Guo

The diverse and high-quality content generated by recent generative models demonstrates the great potential of using synthetic data to train downstream models.

Domain Adaptation Head Detection +2

Apple scab detection in orchards using deep learning on colour and multispectral images

no code implementations • 17 Feb 2023 • Robert Rouš, Joseph Peller, Gerrit Polder, Selwin Hageraats, Thijs Ruigrok, Pieter M. Blok

Despite the promising results of deep learning using RGB images (P=0. 8, mAP@50=0. 73), the detection of apple scab in apple trees using multispectral imaging proved to be a difficult task.

Active learning with MaskAL reduces annotation effort for training Mask R-CNN

3 code implementations • 13 Dec 2021 • Pieter M. Blok, Gert Kootstra, Hakim Elchaoui Elghor, Boubacar Diallo, Frits K. van Evert, Eldert J. van Henten

In our study, MaskAL was compared to a random sampling method on a broccoli dataset with five visually similar classes.

Active Learning