Search Results for author:
Found 14 papers, 2 papers with code
SAR Strikes Back: A New Hope for RSVQA
To this purpose, we also present a dataset that allows for the introduction of SAR images in the RSVQA framework.
An LLM Agent for Automatic Geospatial Data Analysis
In addition, we contribute a new benchmark specifically designed to evaluate the LLM-based approach in geospatial tasks.
Can SAR improve RSVQA performance?
In the first one, we explore the classification results of SAR alone and investigate the best method to extract information from SAR data.
Segmentation-guided Attention for Visual Question Answering from Remote Sensing Images
Visual Question Answering for Remote Sensing (RSVQA) is a task that aims at answering natural language questions about the content of a remote sensing image.
The curse of language biases in remote sensing VQA: the role of spatial attributes, language diversity, and the need for clear evaluation
While new, improved and less-biased datasets appear as a necessity for the development of the promising field of RSVQA, we demonstrate that more informed, relative evaluation metrics remain much needed to transparently communicate results of future RSVQA methods.
Deep learning for classification of noisy QR codes
We wish to define the limits of a classical classification model based on deep learning when applied to abstract images, which do not represent visually identifiable objects. QR codes (Quick Response codes) fall into this category of abstract images: one bit corresponding to one encoded character, QR codes were not designed to be decoded manually.
How to find a good image-text embedding for remote sensing visual question answering?
Visual question answering (VQA) has recently been introduced to remote sensing to make information extraction from overhead imagery more accessible to everyone.
Contextual Semantic Interpretability
Once the attributes are learned, they can be re-combined to reach the final decision and provide both an accurate prediction and an explicit reasoning behind the CNN decision.
RSVQA: Visual Question Answering for Remote Sensing Data
We report the results obtained by applying a model based on Convolutional Neural Networks (CNNs) for the visual part and on a Recurrent Neural Network (RNN) for the natural language part to this task.
Semantically Interpretable Activation Maps: what-where-how explanations within CNNs
This gives the user insight into what the model has seen, where, and a final output directly linked to this information in a comprehensive and interpretable way.
Half a Percent of Labels is Enough: Efficient Animal Detection in UAV Imagery using Deep CNNs and Active Learning
We present an Active Learning (AL) strategy for re-using a deep Convolutional Neural Network (CNN)-based object detector on a new dataset.
Wasserstein Adversarial Regularization (WAR) on label noise
Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping.
Correcting rural building annotations in OpenStreetMap using convolutional neural networks
Rural building mapping is paramount to support demographic studies and plan actions in response to crisis that affect those areas.
Scale equivariance in CNNs with vector fields
We study the effect of injecting local scale equivariance into Convolutional Neural Networks.
