STORRE Collection: Electronic copies of Computing Science and Mathematics conference papers and proceedings.
http://hdl.handle.net/1893/478
Electronic copies of Computing Science and Mathematics conference papers and proceedings.2024-03-23T00:21:17ZMTLSegFormer: Multi-Task Learning With Transformers for Semantic Segmentation in Precision Agriculture
http://hdl.handle.net/1893/35587
Title: MTLSegFormer: Multi-Task Learning With Transformers for Semantic Segmentation in Precision Agriculture
Author(s): Goncalves, Diogo Nunes; Junior, Jose Marcato; Zamboni, Pedro; Pistori, Hemerson; Li, Jonathan; Nogueira, Keiller; Goncalves, Wesley
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.2023-01-01T00:00:00ZPrototypical Contrastive Network for Imbalanced Aerial Image Segmentation
http://hdl.handle.net/1893/35585
Title: Prototypical Contrastive Network for Imbalanced Aerial Image Segmentation
Author(s): Nogueira, Keiller; Maezano Faita-Pinheiro, Mayara; Ramos, Ana Paula; Gonçalves, Wesley Nunes; Marcato Junior, José; Santos, Jefersson A Dos
Abstract: Binary segmentation is the main task underpinning several remote sensing applications, which are particularly interested in identifying and monitoring a specific cate-gory/object. Although extremely important, such a task has several challenges, including huge intra-class variance for the background and data imbalance. Furthermore, most works tackling this task partially or completely ignore one or both of these challenges and their developments. In this paper, we propose a novel method to perform imbal-anced binary segmentation of remote sensing images based on deep networks, prototypes, and contrastive loss. The proposed approach allows the model to focus on learning the foreground class while alleviating the class imbalance problem by allowing it to concentrate on the most difficult background examples. The results demonstrate that the proposed method outperforms state-of-the-art techniques for imbalanced binary segmentation of remote sensing images while taking much less training time.Paving the Way for Automatic Mapping of Rural Roads in the Amazon Rainforest
http://hdl.handle.net/1893/35584
Title: Paving the Way for Automatic Mapping of Rural Roads in the Amazon Rainforest
Author(s): Faria, Lucas Costa de; Brito, Matheus; Nogueira, Keiller; dos Santos, Jefersson AEvaluating Explanations for Software Patches Generated by Large Language Models
http://hdl.handle.net/1893/35519
Title: Evaluating Explanations for Software Patches Generated by Large Language Models
Author(s): Sobania, Dominik; Geiger, Alina; Callan, James; Brownlee, Alexander; Hanna, Carol; Moussa, Rebecca; Zamorano López, Mar; Petke, Justyna; Sarro, Federica
Abstract: Large language models (LLMs) have recently been integrated in a variety of applications including software engineering tasks. In this work, we study the use of LLMs to enhance the explainability of software patches. In particular, we evaluate the performance of GPT 3.5 in explaining patches generated by the search-based automated program repair system ARJA-e for 30 bugs from the popular Defects4J benchmark. We also investigate the performance achieved when explaining the corresponding patches written by software developers. We find that on average 84% of the LLM explanations for machine-generated patches were correct and 54% were complete for the studied categories in at least 1 out of 3 runs. Furthermore, we find that the LLM generates more accurate explanations for machine-generated patches than for human-written ones.