arXiv subjects

Hanspeter Pfister

Publications and source records attributed to Hanspeter Pfister.

162 records · Page 9Linked to original sources

arXiv2017

LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks

Recurrent neural networks, and in particular long short-term memory (LSTM) networks, are a remarkably effective tool for sequence modeling that learn a dense black-box hidden representation of their sequential input. Researchers interested in better understanding these models have studied the changes in hidden state representations over time and noticed some interpretable patterns but also significant noise. In this work, we present LSTMVIS, a visual analysis tool for recurrent neural networks with a focus on understanding these hidden state dynamics. The tool allows users to select a hypothesis input range to focus on local state changes, to match these states changes to similar patterns in a large data set, and to align these results with structural annotations from their domain. We show several use cases of the tool for analyzing specific hidden state properties on dataset containing nesting, phrase structure, and chord progressions, and demonstrate how the tool can be used to isolate patterns for further statistical analysis. We characterize the domain, the different stakeholders, and their goals and tasks.

cs.CL↗

arXiv2017

Understanding Infographics through Textual and Visual Tag Prediction

We introduce the problem of visual hashtag discovery for infographics: extracting visual elements from an infographic that are diagnostic of its topic. Given an infographic as input, our computational approach automatically outputs textual and visual elements predicted to be representative of the infographic content. Concretely, from a curated dataset of 29K large infographic images sampled across 26 categories and 391 tags, we present an automated two step approach. First, we extract the text from an infographic and use it to predict text tags indicative of the infographic content. And second, we use these predicted text tags as a supervisory signal to localize the most diagnostic visual elements from within the infographic i.e. visual hashtags. We report performances on a categorization and multi-label tag prediction problem and compare our proposed visual hashtags to human annotations.

cs.CV↗

arXiv2017

BubbleView: an interface for crowdsourcing image importance maps and tracking visual attention

In this paper, we present BubbleView, an alternative methodology for eye tracking using discrete mouse clicks to measure which information people consciously choose to examine. BubbleView is a mouse-contingent, moving-window interface in which participants are presented with a series of blurred images and click to reveal "bubbles" - small, circular areas of the image at original resolution, similar to having a confined area of focus like the eye fovea. Across 10 experiments with 28 different parameter combinations, we evaluated BubbleView on a variety of image types: information visualizations, natural images, static webpages, and graphic designs, and compared the clicks to eye fixations collected with eye-trackers in controlled lab settings. We found that BubbleView clicks can both (i) successfully approximate eye fixations on different images, and (ii) be used to rank image and design elements by importance. BubbleView is designed to collect clicks on static images, and works best for defined tasks such as describing the content of an information visualization or measuring image importance. BubbleView data is cleaner and more consistent than related methodologies that use continuous mouse movements. Our analyses validate the use of mouse-contingent, moving-window methodologies as approximating eye fixations for different image and task types.

cs.HC↗

arXiv2017

Learning Visual Importance for Graphic Designs and Data Visualizations

Knowing where people look and click on visual designs can provide clues about how the designs are perceived, and where the most important or relevant content lies. The most important content of a visual design can be used for effective summarization or to facilitate retrieval from a database. We present automated models that predict the relative importance of different elements in data visualizations and graphic designs. Our models are neural networks trained on human clicks and importance annotations on hundreds of designs. We collected a new dataset of crowdsourced importance, and analyzed the predictions of our models with respect to ground truth importance and human eye movements. We demonstrate how such predictions of importance can be used for automatic design retargeting and thumbnailing. User studies with hundreds of MTurk participants validate that, with limited post-processing, our importance-driven applications are on par with, or outperform, current state-of-the-art methods, including natural image saliency. We also provide a demonstration of how our importance predictions can be built into interactive design tools to offer immediate feedback during the design process.

cs.HC↗

arXiv2017

Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking

Large databases are often organized by hand-labeled metadata, or criteria, which are expensive to collect. We can use unsupervised learning to model database variation, but these models are often high dimensional, complex to parameterize, or require expert knowledge. We learn low-dimensional continuous criteria via interactive ranking, so that the novice user need only describe the relative ordering of examples. This is formed as semi-supervised label propagation in which we maximize the information gained from a limited number of examples. Further, we actively suggest data points to the user to rank in a more informative way than existing work. Our efficient approach allows users to interactively organize thousands of data points along 1D and 2D continuous sliders. We experiment with datasets of imagery and geometry to demonstrate that our tool is useful for quickly assessing and organizing the content of large databases.

cs.CV↗

arXiv2017

Morphological Error Detection in 3D Segmentations

Deep learning algorithms for connectomics rely upon localized classification, rather than overall morphology. This leads to a high incidence of erroneously merged objects. Humans, by contrast, can easily detect such errors by acquiring intuition for the correct morphology of objects. Biological neurons have complicated and variable shapes, which are challenging to learn, and merge errors take a multitude of different forms. We present an algorithm, MergeNet, that shows 3D ConvNets can, in fact, detect merge errors from high-level neuronal morphology. MergeNet follows unsupervised training and operates across datasets. We demonstrate the performance of MergeNet both on a variety of connectomics data and on a dataset created from merged MNIST images.

cs.CV↗

arXiv2017

Guided Proofreading of Automatic Segmentations for Connectomics

Automatic cell image segmentation methods in connectomics produce merge and split errors, which require correction through proofreading. Previous research has identified the visual search for these errors as the bottleneck in interactive proofreading. To aid error correction, we develop two classifiers that automatically recommend candidate merges and splits to the user. These classifiers use a convolutional neural network (CNN) that has been trained with errors in automatic segmentations against expert-labeled ground truth. Our classifiers detect potentially-erroneous regions by considering a large context region around a segmentation boundary. Corrections can then be performed by a user with yes/no decisions, which reduces variation of information 7.5x faster than previous proofreading methods. We also present a fully-automatic mode that uses a probability threshold to make merge/split decisions. Extensive experiments using the automatic approach and comparing performance of novice and expert users demonstrate that our method performs favorably against state-of-the-art proofreading methods on different connectomics datasets.

cs.CV↗

arXiv2016

A Multi-Pass Approach to Large-Scale Connectomics

The field of connectomics faces unprecedented "big data" challenges. To reconstruct neuronal connectivity, automated pixel-level segmentation is required for petabytes of streaming electron microscopy data. Existing algorithms provide relatively good accuracy but are unacceptably slow, and would require years to extract connectivity graphs from even a single cubic millimeter of neural tissue. Here we present a viable real-time solution, a multi-pass pipeline optimized for shared-memory multicore systems, capable of processing data at near the terabyte-per-hour pace of multi-beam electron microscopes. The pipeline makes an initial fast-pass over the data, and then makes a second slow-pass to iteratively correct errors in the output of the fast-pass. We demonstrate the accuracy of a sparse slow-pass reconstruction algorithm and suggest new methods for detecting morphological errors. Our fast-pass approach provided many algorithmic challenges, including the design and implementation of novel shallow convolutional neural nets and the parallelization of watershed and object-merging techniques. We use it to reconstruct, from image stack to skeletons, the full dataset of Kasthuri et al. (463 GB capturing 120,000 cubic microns) in a matter of hours on a single multicore machine rather than the weeks it has taken in the past on much larger distributed systems.

q-bio.QM↗

arXiv2016

RhoanaNet Pipeline: Dense Automatic Neural Annotation

Reconstructing a synaptic wiring diagram, or connectome, from electron microscopy (EM) images of brain tissue currently requires many hours of manual annotation or proofreading (Kasthuri and Lichtman, 2010; Lichtman and Sanes, 2008; Seung, 2009). The desire to reconstruct ever larger and more complex networks has pushed the collection of ever larger EM datasets. A cubic millimeter of raw imaging data would take up 1 PB of storage and present an annotation project that would be impractical without relying heavily on automatic segmentation methods. The RhoanaNet image processing pipeline was developed to automatically segment large volumes of EM data and ease the burden of manual proofreading and annotation. Based on (Kaynig et al., 2015), we updated every stage of the software pipeline to provide better throughput performance and higher quality segmentation results. We used state of the art deep learning techniques to generate improved membrane probability maps, and Gala (Nunez-Iglesias et al., 2014) was used to agglomerate 2D segments into 3D objects. We applied the RhoanaNet pipeline to four densely annotated EM datasets, two from mouse cortex, one from cerebellum and one from mouse lateral geniculate nucleus (LGN). All training and test data is made available for benchmark comparisons. The best segmentation results obtained gave $V^\text{Info}_\text{F-score}$ scores of 0.9054 and 09182 for the cortex datasets, 0.9438 for LGN, and 0.9150 for Cerebellum. The RhoanaNet pipeline is open source software. All source code, training data, test data, and annotations for all four benchmark datasets are available at www.rhoana.org.

q-bio.NC↗

arXiv2016

Icon: An Interactive Approach to Train Deep Neural Networks for Segmentation of Neuronal Structures

We present an interactive approach to train a deep neural network pixel classifier for the segmentation of neuronal structures. An interactive training scheme reduces the extremely tedious manual annotation task that is typically required for deep networks to perform well on image segmentation problems. Our proposed method employs a feedback loop that captures sparse annotations using a graphical user interface, trains a deep neural network based on recent and past annotations, and displays the prediction output to users in almost real-time. Our implementation of the algorithm also allows multiple users to provide annotations in parallel and receive feedback from the same classifier. Quick feedback on classifier performance in an interactive setting enables users to identify and label examples that are more important than others for segmentation purposes. Our experiments show that an interactively-trained pixel classifier produces better region segmentation results on Electron Microscopy (EM) images than those generated by a network of the same architecture trained offline on exhaustive ground-truth labels.

cs.CV↗

arXiv2016

Context-guided diffusion for label propagation on graphs

Existing approaches for diffusion on graphs, e.g., for label propagation, are mainly focused on isotropic diffusion, which is induced by the commonly-used graph Laplacian regularizer. Inspired by the success of diffusivity tensors for anisotropic diffusion in image processing, we presents anisotropic diffusion on graphs and the corresponding label propagation algorithm. We develop positive definite diffusivity operators on the vector bundles of Riemannian manifolds, and discretize them to diffusivity operators on graphs. This enables us to easily define new robust diffusivity operators which significantly improve semi-supervised learning performance over existing diffusion algorithms.

cs.CV↗

arXiv2016

Semi-supervised Learning with Explicit Relationship Regularization

In many learning tasks, the structure of the target space of a function holds rich information about the relationships between evaluations of functions on different data points. Existing approaches attempt to exploit this relationship information implicitly by enforcing smoothness on function evaluations only. However, what happens if we explicitly regularize the relationships between function evaluations? Inspired by homophily, we regularize based on a smooth relationship function, either defined from the data or with labels. In experiments, we demonstrate that this significantly improves the performance of state-of-the-art algorithms in semi-supervised classification and in spectral data embedding for constrained clustering and dimensionality reduction.

cs.CV↗

arXiv2016

Local High-order Regularization on Data Manifolds

The common graph Laplacian regularizer is well-established in semi-supervised learning and spectral dimensionality reduction. However, as a first-order regularizer, it can lead to degenerate functions in high-dimensional manifolds. The iterated graph Laplacian enables high-order regularization, but it has a high computational complexity and so cannot be applied to large problems. We introduce a new regularizer which is globally high order and so does not suffer from the degeneracy of the graph Laplacian regularizer, but is also sparse for efficient computation in semi-supervised learning applications. We reduce computational complexity by building a local first-order approximation of the manifold as a surrogate geometry, and construct our high-order regularizer based on local derivative evaluations therein. Experiments on human body shape and pose analysis demonstrate the effectiveness and efficiency of our method.

cs.CV↗

arXiv2015

VESICLE: Volumetric Evaluation of Synaptic Interfaces using Computer vision at Large Scale

An open challenge problem at the forefront of modern neuroscience is to obtain a comprehensive mapping of the neural pathways that underlie human brain function; an enhanced understanding of the wiring diagram of the brain promises to lead to new breakthroughs in diagnosing and treating neurological disorders. Inferring brain structure from image data, such as that obtained via electron microscopy (EM), entails solving the problem of identifying biological structures in large data volumes. Synapses, which are a key communication structure in the brain, are particularly difficult to detect due to their small size and limited contrast. Prior work in automated synapse detection has relied upon time-intensive biological preparations (post-staining, isotropic slice thicknesses) in order to simplify the problem. This paper presents VESICLE, the first known approach designed for mammalian synapse detection in anisotropic, non-post-stained data. Our methods explicitly leverage biological context, and the results exceed existing synapse detection methods in terms of accuracy and scalability. We provide two different approaches - one a deep learning classifier (VESICLE-CNN) and one a lightweight Random Forest approach (VESICLE-RF) to offer alternatives in the performance-scalability space. Addressing this synapse detection challenge enables the analysis of high-throughput imaging data soon expected to reach petabytes of data, and provide tools for more rapid estimation of brain-graphs. Finally, to facilitate community efforts, we developed tools for large-scale object detection, and demonstrated this framework to find $\approx$ 50,000 synapses in 60,000 $μm ^3$ (220 GB on disk) of electron microscopy data.

cs.CV↗

arXiv2013

Large-Scale Automatic Reconstruction of Neuronal Processes from Electron Microscopy Images

Automated sample preparation and electron microscopy enables acquisition of very large image data sets. These technical advances are of special importance to the field of neuroanatomy, as 3D reconstructions of neuronal processes at the nm scale can provide new insight into the fine grained structure of the brain. Segmentation of large-scale electron microscopy data is the main bottleneck in the analysis of these data sets. In this paper we present a pipeline that provides state-of-the art reconstruction performance while scaling to data sets in the GB-TB range. First, we train a random forest classifier on interactive sparse user annotations. The classifier output is combined with an anisotropic smoothing prior in a Conditional Random Field framework to generate multiple segmentation hypotheses per image. These segmentations are then combined into geometrically consistent 3D objects by segmentation fusion. We provide qualitative and quantitative evaluation of the automatic segmentation and demonstrate large-scale 3D reconstructions of neuronal processes from a $\mathbf{27,000}$ $\mathbf{μm^3}$ volume of brain tissue over a cube of $\mathbf{30 \; μm}$ in each dimension corresponding to 1000 consecutive image sections. We also introduce Mojo, a proofreading tool including semi-automated correction of merge errors based on sparse user scribbles.

q-bio.NC↗

arXiv2012

Visualization in Connectomics

Connectomics is a field of neuroscience that analyzes neuronal connections. A connectome is a complete map of a neuronal system, comprising all neuronal connections between its structures. The term "connectome" is close to the word "genome" and implies completeness of all neuronal connections, in the same way as a genome is a complete listing of all nucleotide sequences. The goal of connectomics is to create a complete representation of the brain's wiring. Such a representation is believed to increase our understanding of how functional brain states emerge from their underlying anatomical structure. Furthermore, it can provide important information for the cure of neuronal dysfunctions like schizophrenia or autism. In this paper, we review the current state-of-the-art of visualization and image processing techniques in the field of connectomics and describe some remaining challenges.

cs.GR↗

arXiv2012

Verifiable Computation with Massively Parallel Interactive Proofs

As the cloud computing paradigm has gained prominence, the need for verifiable computation has grown increasingly urgent. The concept of verifiable computation enables a weak client to outsource difficult computations to a powerful, but untrusted, server. Protocols for verifiable computation aim to provide the client with a guarantee that the server performed the requested computations correctly, without requiring the client to perform the computations herself. By design, these protocols impose a minimal computational burden on the client. However, existing protocols require the server to perform a large amount of extra bookkeeping in order to enable a client to easily verify the results. Verifiable computation has thus remained a theoretical curiosity, and protocols for it have not been implemented in real cloud computing systems. Our goal is to leverage GPUs to reduce the server-side slowdown for verifiable computation. To this end, we identify abundant data parallelism in a state-of-the-art general-purpose protocol for verifiable computation, originally due to Goldwasser, Kalai, and Rothblum, and recently extended by Cormode, Mitzenmacher, and Thaler. We implement this protocol on the GPU, obtaining 40-120x server-side speedups relative to a state-of-the-art sequential implementation. For benchmark problems, our implementation reduces the slowdown of the server to factors of 100-500x relative to the original computations requested by the client. Furthermore, we reduce the already small runtime of the client by 100x. Similarly, we obtain 20-50x server-side and client-side speedups for related protocols targeted at specific streaming problems. We believe our results demonstrate the immediate practicality of using GPUs for verifiable computation, and more generally that protocols for verifiable computation have become sufficiently mature to deploy in real cloud computing systems.

cs.DC↗

arXiv2010

The Murchison Widefield Array

It is shown that the excellent Murchison Radio-astronomy Observatory site allows the Murchison Widefield Array to employ a simple RFI blanking scheme and still calibrate visibilities and form images in the FM radio band. The techniques described are running autonomously in our calibration and imaging software, which is currently being used to process an FM-band survey of the entire southern sky.

astro-ph.IM↗