MTLSegFormer: Multi-Task Learning With Transformers for Semantic Segmentation in Precision Agriculture

Citation

Goncalves DN, Junior JM, Zamboni P, Pistori H, Li J, Nogueira K & Goncalves W (2023) MTLSegFormer: Multi-Task Learning With Transformers for Semantic Segmentation in Precision Agriculture. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, BC, Canada, 18.06.2023-22.06.2023. Piscataway, NJ, USA: IEEE, pp. 6290-6298. https://doi.org/10.1109/CVPRW59228.2023.00669

Abstract
Multi-task learning has proven to be effective in improving the performance of correlated tasks. Most of the existing methods use a backbone to extract initial features with independent branches for each task, and the exchange of information between the branches usually occurs through the concatenation or sum of the feature maps of the branches. However, this type of information exchange does not directly consider the local characteristics of the image nor the level of importance or correlation between the tasks. In this paper, we propose a semantic segmentation method, MTLSegFormer, which combines multi-task learning and attention mechanisms. After the backbone feature extraction, two feature maps are learned for each task. The first map is proposed to learn features related to its task, while the second map is obtained by applying learned visual attention to locally re-weigh the feature maps of the other tasks. In this way, weights are assigned to local regions of the image of other tasks that have greater importance for the specific task. Finally, the two maps are combined and used to solve a task. We tested the performance in two challenging problems with correlated tasks and observed a significant improvement in accuracy, mainly in tasks with high dependence on the others.

Keywords
Visualization; Shape , Semantic segmentation; Feature extraction; Transformers; Multitasking; Decoding