Continual Learning Approach for Remote Sensing Scene Classification
By Nassim Ammour, Yakoub Bazi, Haikel Salem Alhichri, Naif Alajlan. 2020
20 citations recorded by the source corpus.
In this letter, we propose a continual learning approach for a set of sequential scene classification tasks, where each task contains a group of land-cover classes. Our aim is to learn new tasks in a continual way without significantly degrading the performances of the old ones, due to the tricky catastrophic forgetting problem inherent to neural networks. To this end, we propose a neural architecture composed of two trainable modules. The first module learns its weights by discriminating between the land-cover classes within the new task while keeping trace of the old ones. On the other side, the second module tries to maximize the separation between the tasks by learning on task-prototypes stored in a linear memory (one prototype per task). The experimental results on two scene data sets (Merced and Optimal31) confirm the promising capability of the proposed method.
Subfields: Artificial Intelligence, Computational Mechanics, Media Technology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Valerio Marsocci
- Simone Scardapane
- S. Divakar Bhat
- Subhasis Chaudhuri
- Nassim Ammour
- Biplab Banerjee
- Laura Palagi
In Computational Mechanics
In Media Technology
Citations in the corpus
- Continual Barlow Twins: Continual Self-Supervised Learning for Remote Sensing Semantic Segmentation (2022, background): “In fact, in RS, there are several CL benchmarks focused on incremental annotation of land cover classes [5], [25], [26], but the case where images with different characteristics arrive in a continual scenario is underexplored.”
- Continual Learning Using Data Regeneration for Remote Sensing Scene Classification (2022, methodology): “The second method is proposed in [15], and this method is similar to the method proposed in [14] except it uses a task selector.”
- CILEA-NET: Curriculum-Based Incremental Learning Framework for Remote Sensing Image Classification (2021, methodology): “Similarly,wecom-parewith[31],whichisareplay-basedapproachinremote sensing.”