41 citations · 109 across the 14 of their papers we have counts for
18 papers
Recognition of Unseen Bird Species by Learning from Field Guides
Andrés C. Rodríguez, Stefano D'Aronco, Rodrigo Caye Daudt +2
We exploit field guides to learn bird species recognition, in particular zero-shot recognition of unseen species. Illustrations contained in field guides deliberately focus on disc…
FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation
Mehmet Ozgur Turkoglu, Alexander Becker, Hüseyin Anil Gündüz +6
The ability to estimate epistemic uncertainty is often crucial when deploying machine learning in the real world, but modern methods often produce overconfident, uncalibrated uncer…
A Deep Learning Approach for Digital Color Reconstruction of Lenticular Films
Stefano D'Aronco, Giorgio Trumpy, David Pfluger +1
We propose the first accurate digitization and color reconstruction process for historical lenticular film that is robust to artifacts. Lenticular films emerged in the 1920s and we…
Learning Graph Regularisation for Guided Super-Resolution
Riccardo de Lutio, Alexander Becker, Stefano D'Aronco +3
We introduce a novel formulation for guided super-resolution. Its core is a differentiable optimisation layer that operates on a learned affinity graph. The learned graph potential…
Digital Taxonomist: Identifying Plant Species in Community Scientists' Photographs
Riccardo de Lutio, Yihang She, Stefano D'Aronco +4
Automatic identification of plant specimens from amateur photographs could improve species range maps, thus supporting ecosystems research as well as conservation efforts. However,…
Mapping oil palm density at country scale: An active learning approach
Andrés C. Rodríguez, Stefano D'Aronco, Konrad Schindler +1
Accurate mapping of oil palm is important for understanding its past and future impact on the environment. We propose to map and count oil palms by estimating tree densities per pi…
PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds
Yujia Liu, Stefano D'Aronco, Konrad Schindler +1
We introduce PC2WF, the first end-to-end trainable deep network architecture to convert a 3D point cloud into a wireframe model. The network takes as input an unordered set of 3D p…
Crop mapping from image time series: deep learning with multi-scale label hierarchies
Mehmet Ozgur Turkoglu, Stefano D'Aronco, Gregor Perich +4
The aim of this paper is to map agricultural crops by classifying satellite image time series. Domain experts in agriculture work with crop type labels that are organised in a hier…
Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations
Nando Metzger, Mehmet Ozgur Turkoglu, Stefano D'Aronco +2
Optical satellite sensors cannot see the Earth's surface through clouds. Despite the periodic revisit cycle, image sequences acquired by Earth observation satellites are therefore…
Deep Active Learning in Remote Sensing for data efficient Change Detection
Vít Růžička, Stefano D'Aronco, Jan Dirk Wegner +1
We investigate active learning in the context of deep neural network models for change detection and map updating. Active learning is a natural choice for a number of remote sensin…
Water level prediction from social media images with a multi-task ranking approach
P. Chaudhary, S. D'Aronco, J. P. Leitao +2
Floods are among the most frequent and catastrophic natural disasters and affect millions of people worldwide. It is important to create accurate flood maps to plan (offline) and c…
GeoGraph: Learning graph-based multi-view object detection with geometric cues end-to-end
Ahmed Samy Nassar, Stefano D'Aronco, Sébastien Lefèvre +1
In this paper we propose an end-to-end learnable approach that detects static urban objects from multiple views, re-identifies instances, and finally assigns a geographic position…
Fine-grained Species Recognition with Privileged Pooling: Better Sample Efficiency Through Supervised Attention
Andres C. Rodriguez, Stefano D'Aronco, Konrad Schindler +1
We propose a scheme for supervised image classification that uses privileged information, in the form of keypoint annotations for the training data, to learn strong models from sma…
Gating Revisited: Deep Multi-layer RNNs That Can Be Trained
Mehmet Ozgur Turkoglu, Stefano D'Aronco, Jan Dirk Wegner +1
We propose a new STAckable Recurrent cell (STAR) for recurrent neural networks (RNNs), which has fewer parameters than widely used LSTM and GRU while being more robust against vani…
Guided Super-Resolution as Pixel-to-Pixel Transformation
Riccardo de Lutio, Stefano D'Aronco, Jan Dirk Wegner +1
Guided super-resolution is a unifying framework for several computer vision tasks where the inputs are a low-resolution source image of some target quantity (e.g., perspective dept…
Online Resource Inference in Network Utility Maximization Problems
Stefano D'Aronco, Pascal Frossard
The amount of transmitted data in computer networks is expected to grow considerably in the future, putting more and more pressure on the network infrastructures. In order to guara…
Price-based Controller for Quality-Fair HTTP Adaptive Streaming (Extended Version)
Stefano D'Aronco, Laura Toni, Pascal Frossard
HTTP adaptive streaming (HAS) has become the universal technology for video streaming over the Internet. Many HAS system designs aim at sharing the network bandwidth in a rate-fair…
Improved Utility-based Congestion Control for Delay-Constrained Communication
Stefano D'Aronco, Laura Toni, Sergio Mena +2
Due to the presence of buffers in the inner network nodes, each congestion event leads to buffer queueing and thus to an increasing end-to-end delay. In the case of delay sensitive…