Mahsa Baktashmotlagh

Unsupervised Domain Adaptation by Domain Invariant Projection

Domain-invariant representations are key to addressing the domain shift problem where the training and test examples follow different distributions. Existing techniques that have attempted to match the distributions of the source and target domains typically compare these distributions in the original feature space. This space, however, may not be directly suitable for such a comparison, since some of the features may have been distorted by the domain shift, or may be domain specific. In this paper, we introduce a Domain Invariant Projection approach: An unsupervised domain adaptation method that overcomes this issue by extracting the information that is invariant across the source and target domains. More specifically, we learn a projection of the data to a low-dimensional latent space where the distance between the empirical distributions of the source and target examples is minimized. We demonstrate the effectiveness of our approach on the task of visual object recognition and show that it outperforms state-of-the-art methods on a standard domain adaptation benchmark dataset.

Domain Adaptation on the Statistical Manifold

In this paper, we tackle the problem of unsupervised domain adaptation for classification. In the unsupervised scenario where no labeled samples from the target domain are provided, a popular approach consists in transforming the data such that the source and target distributions become similar. To compare the two distributions, existing approaches make use of the Maximum Mean Discrepancy (MMD). However, this does not exploit the fact that probability distributions lie on a Riemannian manifold. Here, we propose to make better use of the structure of this manifold and rely on the distance on the manifold to compare the source and target distributions. In this framework, we introduce a sample selection method and a subspace-based method for unsupervised domain adaptation, and show that both these manifold-based techniques outperform the corresponding approaches based on the MMD. Furthermore, we show that our subspace-based approach yields state-of-the-art results on a standard object recognition benchmark.

Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs

State-of-the-art image-set matching techniques typically implicitly model each image-set with a Gaussian distribution. Here, we propose to go beyond these representations and model image-sets as probability distribution functions (PDFs) using kernel density estimators. To compare and match image-sets, we exploit Csiszar f-divergences, which bear strong connections to the geodesic distance defined on the space of PDFs, i.e., the statistical manifold. Furthermore, we introduce valid positive definite kernels on the statistical manifolds, which let us make use of more powerful classification schemes to match image-sets. Finally, we introduce a supervised dimensionality reduction technique that learns a latent space where f-divergences reflect the class labels of the data. Our experiments on diverse problems, such as video-based face recognition and dynamic texture classification, evidence the benefits of our approach over the state-of-the-art image-set matching methods.

Discriminative non-linear stationary subspace analysis for video classification

Low-dimensional representations are key to the success of many video classification algorithms. However, the commonly-used dimensionality reduction techniques fail to account for the fact that only part of the signal is shared across all the videos in one class. As a consequence, the resulting representations contain instance-specific information, which introduces noise in the classification process. In this paper, we introduce non-linear stationary subspace analysis: a method that overcomes this issue by explicitly separating the stationary parts of the video signal (i.e., the parts shared across all videos in one class), from its non-stationary parts (i.e., the parts specific to individual videos). Our method also encourages the new representation to be discriminative, thus accounting for the underlying classification problem. We demonstrate the effectiveness of our approach on dynamic texture recognition, scene classification and action recognition.

A wireless mesh sensor network for hazard and safety monitoring at the Port of Brisbane

A wireless sensor network (WSN) was designed and implemented to provide reliable long-term hazard monitoring at the Port of Brisbane, Australia. The proposed system consists of four sensor nodes, a wireless gateway and a central monitoring computer. The sensor nodes are capable of measuring a range of hazardous events along with the time and location of events in maritime environment. Each sensor node is also equipped with a Global Positioning System (GPS) module and a ZigBee module. The monitoring server is a personal computer application server with Internet connectivity. Sensor nodes utilize smart algorithm to save energy and AES-128 encryption to encode data prior to sending the data packet through the wireless ZigBee protocol to gateway. The gateway collects and decrypts the data packets and forwards them to the monitoring computer through wireless connection. A database server running on the monitoring computer stores the captured data for visualization and further analysis. The monitoring server is interfaced to Google Maps to overlay real-time data from the sensor nodes onto map in the correct corresponding locations. The WSN system was successfully deployed and tested at the Port of Brisbane, Queensland, Australia.

Learning Domain Invariant Embeddings by Matching Distributions

One of the characteristics of the domain shift problem is that the source and target data have been drawn from different distributions. A natural approach to addressing this problem therefore consists of learning an embedding of the source and target data such that they have similar distributions in the new space. In this chapter, we study several methods that follow this approach. At the core of these methods lies the notion of distance between two distributions. We first discuss domain adaptation (DA) techniques that rely on the Maximum Mean Discrepancy to measure such a distance. We then study the use of alternative distribution distance measures within one specific Domain Adaptation framework. In this context, we focus on f-divergences, and in particular on the KL divergence and the Hellinger distance. Throughout the chapter, we evaluate the different methods and distance measures on the task of visual object recognition and compare them against related baselines on a standard DA benchmark dataset.

R1STM: one-class support tensor machine with randomised kernel

Identifying unusual or anomalous patterns in an underlying dataset is an important but challenging task in many applications. The focus of the unsupervised anomaly detection literature has mostly been on vectorised data. However, many applications are more naturally described using higher-order tensor representations. Approaches that vectorise tensorial data can destroy the structural information encoded in the high-dimensional space, and lead to the problem of the curse of dimensionality. In this paper we present the first unsupervised tensorial anomaly detection method, along with a randomised version of our method. Our anomaly detection method, the One-class Support Tensor Machine (1STM), is a generalisation of conventional one-class Support Vector Machines to higher-order spaces. 1STM preserves the multiway structure of tensor data, while achieving significant improvement in accuracy and efficiency over conventional vectorised methods. We then leverage the theory of nonlinear random projections to propose the Randomised 1STM (R1STM). Our empirical analysis on several real and synthetic datasets shows that our R1STM algorithm delivers comparable or better accuracy to a state-of-the-art deep learning method and traditional kernelised approaches for anomaly detection, while being approximately 100 times faster in training and testing.