Samuel Rota Bulò

Samuel Rota Bulò

Auto-generated profile, based on publicly available information

Samuel Rota Bulò

Meta Reality Labs Zurich

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2011
Verified
Conference Paper
Closed access
PKPeter Kontschieder
Peter Kontschieder
SBSamuel Rota Bulo
Samuel Rota Bulo
HBHorst Bischof
Horst Bischof
MPMarcello Pelillo
Marcello Pelillo
In this paper we propose a simple and effective way to integrate structural information in random forests for semantic image labelling. By structural information we refer to the inherently available, topological distribution of object classes in a given image. Different object class labels will not be randomly distributed over an image but usually form coherently labelled regions. In this work we provide a way to incorporate this topological information in the popular random forest framework for performing low-level, unary classification. Our paper has several contributions: First, we show how random forests can be augmented with structured label information. In the second part, we introduce a novel data splitting function that exploits the joint distributions observed in the structured label space for learning typical label transitions between object classes. Finally, we provide two possibilities for integrating the structured output predictions into concise, semantic labellings. In our experiments on the challenging MSRC and CamVid databases, we compare our method to standard random forest and conditional random field classification results.

1 June 2014
Verified
Conference Paper
Closed access
EREmanuele Rodola
Emanuele Rodola
SBSamuel Rota Bulo
Samuel Rota Bulo
TWThomas Windheuser
Thomas Windheuser
MVMatthias Vestner
Matthias Vestner
DCDaniel Cremers
Daniel Cremers
We propose a shape matching method that produces dense correspondences tuned to a specific class of shapes and deformations. In a scenario where this class is represented by a small set of example shapes, the proposed method learns a shape descriptor capturing the variability of the deformations in the given class. The approach enables the wave kernel signature to extend the class of recognized deformations from near isometries to the deformations appearing in the example set by means of a random forest classifier. With the help of the introduced spatial regularization, the proposed method achieves significant improvements over the baseline approach and obtains state-of-the-art results while keeping short computation times.

15 October 2012 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SBSamuel Rota Bulo
Samuel Rota Bulo
MPMarcello Pelillo
Marcello Pelillo
Hypergraph clustering refers to the process of extracting maximally coherent groups from a set of objects using high-order (rather than pairwise) similarities. Traditional approaches to this problem are based on the idea of partitioning the input data into a predetermined number of classes, thereby obtaining the clusters as a by-product of the partitioning process. In this paper, we offer a radically different view of the problem. In contrast to the classical approach, we attempt to provide a meaningful formalization of the very notion of a cluster and we show that game theory offers an attractive and unexplored perspective that serves our purpose well. To this end, we formulate the hypergraph clustering problem in terms of a noncooperative multiplayer clustering game, and show that a natural notion of a cluster turns out to be equivalent to a classical (evolutionary) game-theoretic equilibrium concept. We prove that the problem of finding the equilibria of our clustering game is equivalent to locally optimizing a polynomial function over the standard simplex, and we provide a discrete-time high-order replicator dynamics to perform this optimization, based on the Baum-Eagon inequality. Experiments over synthetic as well as real-world data are presented which show the superiority of our approach over the state of the art.

18 September 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
ASAndrea Simonelli
Andrea Simonelli
SBSamuel Rota Bulo
Samuel Rota Bulo
LPLorenzo Porzi
Lorenzo Porzi
MAManuel Lopez Antequera
Manuel Lopez Antequera
PKPeter Kontschieder
Peter Kontschieder
In this paper we introduce a method for multi-class, monocular 3D object detection from a single RGB image, which exploits a novel disentangling transformation and a novel, self-supervised confidence estimation method for predicted 3D bounding boxes. The proposed disentangling transformation isolates the contribution made by different groups of parameters to a given loss, without changing its nature. This brings two advantages: i) it simplifies the training dynamics in the presence of losses with complex interactions of parameters, and ii) it allows us to avoid the issue of balancing independent regression terms. We further apply this disentangling transformation to another novel, signed Intersection-over-Union criterion-driven loss for improving 2D detection results. We also critically review the AP metric used in KITTI3D and resolve a flaw which affected and biased all previously published results on monocular 3D detection. Our improved metric is now used as official KITTI3D metric. We provide extensive experimental evaluations and ablation studies on the KITTI3D and nuScenes datasets, setting new state-of-the-art results. We provide additional results on all the classes of KITTI3D as well as nuScenes datasets to further validate the robustness of our method, demonstrating its ability to generalize for different types of objects.

21 November 2024
Verified
Book Chapter
Closed access
PDF file
SBSamuel Rota Bulò
Samuel Rota Bulò
LPLorenzo Porzi
Lorenzo Porzi
PKPeter Kontschieder
Peter Kontschieder

4 November 2013
Verified
Conference Paper
Open access
PDF file
BBBattista Biggio
Battista Biggio
IPIgnazio Pillai
Ignazio Pillai
SBSamuel Rota Bulò
Samuel Rota Bulò
DADavide Ariu
Davide Ariu
MPMarcello Pelillo
Marcello Pelillo
FRFabio Roli
Fabio Roli
Clustering algorithms have been increasingly adopted in security applications to spot dangerous or illicit activities. However, they have not been originally devised to deal with deliberate attack attempts that may aim to subvert the clustering process itself. Whether clustering can be safely adopted in such settings remains thus questionable. In this work we propose a general framework that allows one to identify potential attacks against clustering algorithms, and to evaluate their impact, by making specific assumptions on the adversary's goal, knowledge of the attacked system, and capabilities of manipulating the input data. We show that an attacker may significantly poison the whole clustering process by adding a relatively small percentage of attack samples to the input data, and that some attack samples may be obfuscated to be hidden within some existing clusters. We present a case study on single-linkage hierarchical clustering, and report experiments on clustering of malware samples and handwritten digits.