5 papers
Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration
Francisco Mena, Dino Ienco, Cassio F. Dantas +2
Multi-modal co-learning is emerging as an effective paradigm in machine learning, enabling models to collaboratively learn from different modalities to enhance single-modality pred…
Fire severity and recovery across Europe: insights from forest diversity and landscape metrics
Eatidal Amin, Cassio F. Dantas, Dino Ienco +2
In recent decades, European forests have faced an increased incidence of fire disturbances. This phenomenon is likely to persist, given the rising frequency of extreme events expec…
Revisiting Cross-Modal Knowledge Distillation: A Disentanglement Approach for RGBD Semantic Segmentation
Roger Ferrod, Cássio F. Dantas, Luigi Di Caro +1
Multi-modal RGB and Depth (RGBD) data are predominant in many domains such as robotics, autonomous driving and remote sensing. The combination of these multi-modal data enhances en…
Geographical Context Matters: Bridging Fine and Coarse Spatial Information to Enhance Continental Land Cover Mapping
Babak Ghassemi, Cassio Fraga-Dantas, Raffaele Gaetano +4
Land use and land cover mapping from Earth Observation (EO) data is a critical tool for sustainable land and resource management. While advanced machine learning and deep learning…
SenCLIP: Enhancing zero-shot land-use mapping for Sentinel-2 with ground-level prompting
Pallavi Jain, Dino Ienco, Roberto Interdonato +2
Pre-trained vision-language models (VLMs), such as CLIP, demonstrate impressive zero-shot classification capabilities with free-form prompts and even show some generalization in sp…