Beyond dataset bias: Multi-task unaligned shared knowledge transfer

Many visual datasets are traditionally used to analyze the performance of different learning techniques. The evaluation is usually done within each dataset, therefore it is questionable if such results are a reliable indicator of true generalization ability. We propose here an algorithm to exploit the existing data resources when learning on a new multiclass problem. Our main idea is to identify an image representation that decomposes orthogonally into two subspaces: a part specific to each dataset, and a part generic to, and therefore shared between, all the considered source sets. This allows us to use the generic representation as un-biased reference knowledge for a novel classification task. By casting the method in the multi-view setting, we also make it possible to use different features for different databases. We call the algorithm MUST, Multitask Unaligned Shared knowledge Transfer. Through extensive experiments on five public datasets, we show that MUST consistently improves the cross-datasets generalization performance. © 2013 Springer-Verlag.

On sparsity and overcompleteness in image models

Computational models of visual cortex, and in particular those based on sparse coding, have enjoyed much recent attention. Despite this currency, the question of how sparse or how over-complete a sparse representation should be, has gone without principled answer. Here, we use Bayesian model-selection methods to address these questions for a sparse-coding model based on a Student-t prior. Having validated our methods on toy data, we find that natural images are indeed best modelled by extremely sparse distributions; although for the Student-t prior, the associated optimal basis size is only modestly over-complete.

An evaluation of space time cube representation of spatiotemporal patterns.

Space time cube representation is an information visualization technique where spatiotemporal data points are mapped into a cube. Information visualization researchers have previously argued that space time cube representation is beneficial in revealing complex spatiotemporal patterns in a data set to users. The argument is based on the fact that both time and spatial information are displayed simultaneously to users, an effect difficult to achieve in other representations. However, to our knowledge the actual usefulness of space time cube representation in conveying complex spatiotemporal patterns to users has not been empirically validated. To fill this gap, we report on a between-subjects experiment comparing novice users' error rates and response times when answering a set of questions using either space time cube or a baseline 2D representation. For some simple questions, the error rates were lower when using the baseline representation. For complex questions where the participants needed an overall understanding of the spatiotemporal structure of the data set, the space time cube representation resulted in on average twice as fast response times with no difference in error rates compared to the baseline. These results provide an empirical foundation for the hypothesis that space time cube representation benefits users analyzing complex spatiotemporal patterns.

The Trade-offs with Space Time Cube Representation of Spatiotemporal Patterns

Space time cube representation is an information visualization technique where spatiotemporal data points are mapped into a cube. Fast and correct analysis of such information is important in for instance geospatial and social visualization applications. Information visualization researchers have previously argued that space time cube representation is beneficial in revealing complex spatiotemporal patterns in a dataset to users. The argument is based on the fact that both time and spatial information are displayed simultaneously to users, an effect difficult to achieve in other representations. However, to our knowledge the actual usefulness of space time cube representation in conveying complex spatiotemporal patterns to users has not been empirically validated. To fill this gap we report on a between-subjects experiment comparing novice users error rates and response times when answering a set of questions using either space time cube or a baseline 2D representation. For some simple questions the error rates were lower when using the baseline representation. For complex questions where the participants needed an overall understanding of the spatiotemporal structure of the dataset, the space time cube representation resulted in on average twice as fast response times with no difference in error rates compared to the baseline. These results provide an empirical foundation for the hypothesis that space time cube representation benefits users when analyzing complex spatiotemporal patterns.

Image deconvolution using a Gaussian scale mixtures model to approximate the wavelet sparseness constraint

This paper proposes to use an extended Gaussian Scale Mixtures (GSM) model instead of the conventional ℓ1 norm to approximate the sparseness constraint in the wavelet domain. We combine this new constraint with subband-dependent minimization to formulate an iterative algorithm on two shift-invariant wavelet transforms, the Shannon wavelet transform and dual-tree complex wavelet transform (DTCWT). This extented GSM model introduces spatially varying information into the deconvolution process and thus enables the algorithm to achieve better results with fewer iterations in our experiments. ©2009 IEEE.

A new method for the acquisition of ultrasonic strain image volumes.

This article presents a new method for acquiring three-dimensional (3-D) volumes of ultrasonic axial strain data. The method uses a mechanically-swept probe to sweep out a single volume while applying a continuously varying axial compression. Acquisition of a volume takes 15-20 s. A strain volume is then calculated by comparing frame pairs throughout the sequence. The method uses strain quality estimates to automatically pick out high quality frame pairs, and so does not require careful control of the axial compression. In a series of in vitro and in vivo experiments, we quantify the image quality of the new method and also assess its ease of use. Results are compared with those for the current best alternative, which calculates strain between two complete volumes. The volume pair approach can produce high quality data, but skillful scanning is required to acquire two volumes with appropriate relative strain. In the new method, the automatic quality-weighted selection of image pairs overcomes this difficulty and the method produces superior quality images with a relatively relaxed scanning technique.

Uplift resistance of buried pipelines at low cover-diameter ratios

Reliable estimates for the maximum available uplift resistance from the backfill soil are essential to prevent upheaval buckling of buried pipelines. The current design code DNV RP F110 does not offer guidance on how to predict the uplift resistance when the cover:pipe diameter (H/D) ratio is less than 2. Hence the current industry practice is to discount the shear contribution from uplift resitance for design scenarios with H/D ratios less than 1. The necessity of this extra conservatism is assessed through a series of full-scale and centrifuge tests, 21 in total, at the Schofield Centre, University of Cambridge. Backfill types include saturated loose sand, saturated dense sand and dry gravel. Data revealed that the Vertical Slip Surface Model remains applicable for design scenarios in loose sand, dense sand and gravel with H/D ratios less than 1, and that there is no evidence that the contribution from shear should be ignored at these low H/D ratios. For uplift events in gravel, the shear component seems reliable if the cover is more than 1-2 times the average particle size (D50), and more research effort is currenty being carried out to verify this conclusion. Strain analysis from the Particle Image Velocimetry (PIV) technique proves that the Vertical Slip Surface Model is a good representation of the true uplift deformation mechanism in loose sand at H/D ratios between 0.5 and 3.5. At very low H/D ratios (H/D < 0.5), the deformation mechanism is more wedge-like, but the increased contribution from soil weight is likely to be compensated by the reduced shear contributions. Hence the design equation based on the Vertical Slip Surface Model still produces good estimates for the maximum available uplift resistance. The evolution of shear strain field from PIV analysis provides useful insight into how uplift resistance is mobilized as the uplift event progresses. Copyright 2010, Offshore Technology Conference.

Combining interest points and edges for content-based image retrieval

This paper presents a novel approach using combined features to retrieve images containing specific objects, scenes or buildings. The content of an image is characterized by two kinds of features: Harris-Laplace interest points described by the SIFT descriptor and edges described by the edge color histogram. Edges and corners contain the maximal amount of information necessary for image retrieval. The feature detection in this work is an integrated process: edges are detected directly based on the Harris function; Harris interest points are detected at several scales and Harris-Laplace interest points are found using the Laplace function. The combination of edges and interest points brings efficient feature detection and high recognition ratio to the image retrieval system. Experimental results show this system has good performance. © 2005 IEEE.

Image-based localization and pose recovery using scale invariant features

In this paper, we propose a vision based mobile robot localization strategy. Local scale-invariant features are used as natural landmarks in unstructured and unmodified environment. The local characteristics of the features we use prove to be robust to occlusion and outliers. In addition, the invariance of the features to viewpoint change makes them suitable landmarks for mobile robot localization. Scale-invariant features detected in the first exploration are indexed into a location database. Indexing and voting allow efficient recognition of global localization. The localization result is verified by epipolar geometry between the representative view in database and the view to be localized, thus the probability of false localization will be decreased. The localization system can recover the pose of the camera mounted on the robot by essential matrix decomposition. Then the position of the robot can be computed easily. Both calibrated and un-calibrated cases are discussed and relative position estimation based on calibrated camera turns out to be the better choice. Experimental results show that our approach is effective and reliable in the case of illumination changes, similarity transformations and extraneous features. © 2004 IEEE.