Related papers: Disentangled Adversarial Autoencoder for Subject-I…
We introduce a framework for dynamic adversarial discovery of information (DADI), motivated by a scenario where information (a feature set) is used by third parties with unknown objectives. We train a reinforcement learning agent to…
Anomaly detection is facing with emerging challenges in many important industry domains, such as cyber security and online recommendation and advertising. The recent trend in these areas calls for anomaly detection on time-evolving data…
Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction as it discards the…
Deep learning models are widely employed in safety-critical applications yet remain susceptible to adversarial attacks -- imperceptible perturbations that can significantly degrade model performance. Conventional defense mechanisms…
Unsupervised learning is of growing interest because it unlocks the potential held in vast amounts of unlabelled data to learn useful representations for inference. Autoencoders, a form of generative model, may be trained by learning to…
The deployment of machine listening algorithms in real-life applications is often impeded by a domain shift caused for instance by different microphone characteristics. In this paper, we propose a novel domain adaptation strategy based on…
This paper addresses two crucial problems of learning disentangled image representations, namely controlling the degree of disentanglement during image editing, and balancing the disentanglement strength and the reconstruction quality. To…
Deep learning models trained on audio-visual data have been successfully used to achieve state-of-the-art performance for emotion recognition. In particular, models trained with multitask learning have shown additional performance…
In real-world scenarios, different features have different acquisition costs at test-time which necessitates cost-aware methods to optimize the cost and performance trade-off. This paper introduces a novel and scalable approach for…
Training models that are robust to data domain shift has gained an increasing interest both in academia and industry. Question-Answering language models, being one of the typical problem in Natural Language Processing (NLP) research, has…
This paper addresses the problem of Human Activity Recognition (HAR) using data from wearable inertial sensors. An important challenge in HAR is the model's generalization capabilities to new unseen individuals due to inter-subject…
Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. Here, our objective is to learn representations that are invariant to…
Fairness is becoming a rising concern w.r.t. machine learning model performance. Especially for sensitive fields such as criminal justice and loan decision, eliminating the prediction discrimination towards a certain group of population…
Data-driven generative 3D face models are used to compactly encode facial shape data into meaningful parametric representations. A desirable property of these models is their ability to effectively decouple natural sources of variation, in…
Multi-agent systems exhibit complex behaviors that emanate from the interactions of multiple agents in a shared environment. In this work, we are interested in controlling one agent in a multi-agent system and successfully learn to interact…
Frequency spectrum has played a significant role in learning unique and discriminating features for object recognition. Both low and high frequency information present in images have been extracted and learnt by a host of representation…
It is well known that humans can learn and recognize objects effectively from several limited image samples. However, learning from just a few images is still a tremendous challenge for existing main-stream deep neural networks. Inspired by…
AI-based sensing at wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications, particularly for vision and perception tasks such as in autonomous driving and environmental monitoring. AI…
Fairness and accountability are two essential pillars for trustworthy Artificial Intelligence (AI) in healthcare. However, the existing AI model may be biased in its decision marking. To tackle this issue, we propose an adversarial…
Thanks to their ability to learn flexible data-driven losses, Generative Adversarial Networks (GANs) are an integral part of many semi- and weakly-supervised methods for medical image segmentation. GANs jointly optimise a generator and an…