Test time augmentation has been shown to be an effective approach to combat domain shifts in deep learning. Despite their promising performance levels, the interpretability of the underlying used models is however low. Saliency maps have been widely used i ...
Multicellular organisms require very well organized and finely balanced cell-cell communication, adhesion and coordination to ensure the organisms homeostasis. These functions rely on specialized receptors placed at the cells membrane whose binding to thei ...
Representing and reconstructing 3D deformable shapes are two tightly linked problems that have long been studied within the computer vision field. Deformable shapes are truly ubiquitous in the real world, whether be it specific object classes such as human ...
Object-centric learning has gained significant attention over the last years as it can serve as a powerful tool to analyze complex scenes as a composition of simpler entities. Well-established tasks in computer vision, such as object detection or instance ...
This thesis assesses the surveillance operated on the mobile phone network by governmental actors (intelligence agencies, police, army) and the relationship between monitored spaces and their users. Indeed, some new surveillance devices used by intelligenc ...
Visual working memory (VWM) is prone to interference from stored items competing for its limited capacity. Distinctiveness or similarity of the items is acknowledged to affect this competition, such that poor item distinctiveness causes a failure to discri ...
In this article, I discuss the process of designing an object to protest against a specific surveillance device: the IMSI catcher, a controversial object used to monitor GSM networks. Being widely used in protests, I develop a tactical approach based on ob ...
In this dissertation, we propose gradient-based methods for characterizing model behaviour for the purposes of knowledge transfer and post-hoc model interpretation. Broadly, gradients capture the variation of some output feature of the model upon unit vari ...
This chapter looks at the intertwined evolution of two different ideas throughout the past century: that of ‘territory’, that has been reshaped and redefined in the field of architecture and urbanism, and that of ‘digital’, that while becoming dominant, ha ...
The successes of deep learning for semantic segmentation can in be, in part, attributed to its scale: a notion that encapsulates the largeness of these computational architectures and the labeled datasets they are trained on. These resource requirements hi ...
