Related papers: Human-interpretable and deep features for image pr…
The remarkable success of machine learning has fostered a growing number of cloud-based intelligent services for mobile users. Such a service requires a user to send data, e.g. image, voice and video, to the provider, which presents a…
The pixels in an image, and the objects, scenes, and actions that they compose, determine whether an image will be memorable or forgettable. While memorability varies by image, it is largely independent of an individual observer. Observer…
This paper studies the problem of measuring and predicting how memorable an image is to pattern recognition machines, as a path to explore machine intelligence. Firstly, we propose a self-supervised machine memory quantification pipeline,…
Differentially private (DP) machine learning is considered the gold-standard solution for training a model from sensitive data while still preserving privacy. However, a major barrier to achieving this ideal is its sub-optimal…
Indoor image features extraction is a fundamental problem in multiple fields such as image processing, pattern recognition, robotics and so on. Nevertheless, most of the existing feature extraction methods, which extract features based on…
Understanding how people represent categories is a core problem in cognitive science. Decades of research have yielded a variety of formal theories of categories, but validating them with naturalistic stimuli is difficult. The challenge is…
The authors discuss their experience applying differential privacy with a complex data set with the goal of enabling standard approaches to statistical data analysis. They highlight lessons learned and roadblocks encountered, distilling…
Differentially private (DP) image synthesis aims to generate artificial images that retain the properties of sensitive images while protecting the privacy of individual images within the dataset. Despite recent advancements, we find that…
Recognising persons in everyday photos presents major challenges (occluded faces, different clothing, locations, etc.) for machine vision. We propose a convnet based person recognition system on which we provide an in-depth analysis of…
Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data…
The evaluation of explainable artificial intelligence is challenging, because automated and human-centred metrics of explanation quality may diverge. To clarify their relationship, we investigated whether human and artificial image…
Local differential privacy (LDP) has become a central topic in data privacy research, offering strong privacy guarantees by perturbing user data at the source and removing the need for a trusted curator. However, the noise introduced by LDP…
Feature selection is the process of sieving features, in which informative features are separated from the redundant and irrelevant ones. This process plays an important role in machine learning, data mining and bioinformatics. However,…
Deep computer vision systems being vulnerable to imperceptible and carefully crafted noise have raised questions regarding the robustness of their decisions. We take a step back and approach this problem from an orthogonal direction. We…
Person Re-identification (re-id) aims to match people across non-overlapping camera views in a public space. It is a challenging problem because many people captured in surveillance videos wear similar clothes. Consequently, the differences…
Estimating perceptual attributes of materials directly from images is a challenging task due to their complex, not fully-understood interactions with external factors, such as geometry and lighting. Supervised deep learning models have…
Representation learning, and interpreting learned representations, are key areas of focus in machine learning and neuroscience. Both fields generally use representations as a means to understand or improve a system's computations. In this…
Humans should be able work more effectively with artificial intelligence-based systems when they can predict likely failures and form useful mental models of how the systems work. We conducted a study of human's mental models of artificial…
Distributed optimization and learning has recently garnered great attention due to its wide applications in sensor networks, smart grids, machine learning, and so forth. Despite rapid development, existing distributed optimization and…
Deep Neural Networks use thousands of mostly incomprehensible features to identify a single class, a decision no human can follow. We propose an interpretable sparse and low dimensional final decision layer in a deep neural network with…