Related papers: DiscreteZOO: a Fingerprint Database of Discrete Ob…
Object recognition and object pose estimation in robotic grasping continue to be significant challenges, since building a labelled dataset can be time consuming and financially costly in terms of data collection and annotation. In this…
The popularity of the Internet of Things (IoT) devices makes it increasingly important to be able to fingerprint them, for example in order to detect if there are misbehaving or even malicious IoT devices in one's network. The aim of this…
We consider training models on private data that are distributed across user devices. To ensure privacy, we add on-device noise and use secure aggregation so that only the noisy sum is revealed to the server. We present a comprehensive…
We introduce a new graphical model for tracking radio-tagged animals and learning their movement patterns. The model provides a principled way to combine radio telemetry data with an arbitrary set of userdefined, spatial features. We…
Federated optimization, an emerging paradigm which finds wide real-world applications such as federated learning, enables multiple clients (e.g., edge devices) to collaboratively optimize a global function. The clients do not share their…
Spectroscopic surveys are undergoing a rapid expansion in their data collecting capabilities, reaching the level of hundreds of spectra per pointing. An efficient use of such huge amounts of information requires a high degree of…
When sharing sensitive relational databases with other parties, a database owner aims to (i) have privacy guarantees for the database entries, (ii) have liability guarantees (via fingerprinting) in case of unauthorized sharing of its…
We introduce the Unity Perception package which aims to simplify and accelerate the process of generating synthetic datasets for computer vision tasks by offering an easy-to-use and highly customizable toolset. This open-source package…
One of the fundamental aspects of ubiquitous computing is the instrumentation of the real world by smart devices. This instrumentation constitutes an opportunity to rethink the interactions between human beings and their environment on the…
Manipulation tools that realistically edit images are widely available, making it easy for anyone to create and spread misinformation. In an attempt to fight fake news, forgery detection and localization methods were designed. However,…
Using synthetic data for training deep neural networks for robotic manipulation holds the promise of an almost unlimited amount of pre-labeled training data, generated safely out of harm's way. One of the key challenges of synthetic data,…
We introduce DeepJoin, an automated approach to generate high-resolution repairs for fractured shapes using deep neural networks. Existing approaches to perform automated shape repair operate exclusively on symmetric objects, require a…
Latent fingerprints are important for identifying criminal suspects. However, recognizing a latent fingerprint in a collection of reference fingerprints remains a challenge. Most, if not all, of existing methods would extract representation…
Similar to humans perceiving visual scenes as objects, Object-Centric Learning (OCL) can abstract dense images or videos into sparse object-level features. Transformer-based OCL handles complex textures well due to the decoding guidance of…
Many ground-breaking advancements in machine learning can be attributed to the availability of a large volume of rich data. Unfortunately, many large-scale datasets are highly sensitive, such as healthcare data, and are not widely available…
Eye contact between individuals is particularly important for understanding human behaviour. To further investigate the importance of eye contact in social interactions, portable eye tracking technology seems to be a natural choice.…
Networks have provided extremely successful models of data and complex systems. Yet, as combinatorial objects, networks do not have in general intrinsic coordinates and do not typically lie in an ambient space. The process of assigning an…
DeeProb-kit is a unified library written in Python consisting of a collection of deep probabilistic models (DPMs) that are tractable and exact representations for the modelled probability distributions. The availability of a representative…
Communication and privacy are two critical concerns in distributed learning. Many existing works treat these concerns separately. In this work, we argue that a natural connection exists between methods for communication reduction and…
Differential privacy (DP) is a compelling privacy definition that explains the privacy-utility tradeoff via formal, provable guarantees. Inspired by recent progress toward general-purpose data release algorithms, we propose a private…