Martin Szummer

Bio: Martin Szummer is an academic researcher from Microsoft. The author has contributed to research in topics: Random walk & Graph (abstract data type). The author has an hindex of 25, co-authored 49 publications receiving 5120 citations. Previous affiliations of Martin Szummer include University of Cambridge & Massachusetts Institute of Technology.

Indoor-outdoor image classification

Abstract: We show how high-level scene properties can be inferred from classification of low-level image features, specifically for the indoor-outdoor scene retrieval problem. We systematically studied the features of: histograms in the Ohta color space; multiresolution, simultaneous autoregressive model parameters; and coefficients of a shift-invariant DCT. We demonstrate that performance is improved by computing features on subblocks, classifying these subblocks, and then combining these results in a way reminiscent of stacking. State of the art single-feature methods are shown to result in about 75-86% performance, while the new method results in 90.3% correct classification, when evaluated on a diverse database of over 1300 consumer images provided by Kodak.

Partially labeled classification with Markov random walks

Abstract: To classify a large number of unlabeled examples we combine a limited number of labeled examples with a Markov random walk representation over the unlabeled examples. The random walk representation exploits any low dimensional structure in the data in a robust, probabilistic manner. We develop and compare several estimation criteria/algorithms suited to this representation. This includes in particular multi-way classification with an average margin criterion which permits a closed form solution. The time scale of the random walk regularizes the representation and can be set through a margin-based criterion favoring unambiguous classification. We also extend this basic regularization by adapting time scales for individual examples. We demonstrate the approach on synthetic examples and on text classification problems.

Random walks on the click graph

Abstract: Search engines can record which documents were clicked for which query, and use these query-document pairs as "soft" relevance judgments. However, compared to the true judgments, click logs give noisy and sparse relevance information. We apply a Markov random walk model to a large click log, producing a probabilistic ranking of documents for a given query. A key advantage of the model is its ability to retrieve relevant documents that have not yet been clicked for that query and rank those effectively. We conduct experiments on click logs from image search, comparing our ("backward") random walk model to a different ("forward") random walk, varying parameters such as walk length and self-transition probability. The most effective combination is a long backward walk with high self-transition probability.

Optimizing Binary MRFs via Extended Roof Duality

Abstract: Many computer vision applications rely on the efficient optimization of challenging, so-called non-submodular, binary pairwise MRFs. A promising graph cut based approach for optimizing such MRFs known as "roof duality" was recently introduced into computer vision. We study two methods which extend this approach. First, we discuss an efficient implementation of the "probing" technique introduced recently by Bows et al. (2006). It simplifies the MRF while preserving the global optimum. Our code is 400-700 faster on some graphs than the implementation of the work of Bows et al. (2006). Second, we present a new technique which takes an arbitrary input labeling and tries to improve its energy. We give theoretical characterizations of local minima of this procedure. We applied both techniques to many applications, including image segmentation, new view synthesis, super-resolution, diagram recognition, parameter learning, texture restoration, and image deconvolution. For several applications we see that we are able to find the global minimum very efficiently, and considerably outperform the original roof duality approach. In comparison to existing techniques, such as graph cut, TRW, BP, ICM, and simulated annealing, we nearly always find a lower energy.

Efficient object category recognition using classemes

Abstract: We introduce a new descriptor for images which allows the construction of efficient and compact classifiers with good accuracy on object category recognition. The descriptor is the output of a large number of weakly trained object category classifiers on the image. The trained categories are selected from an ontology of visual concepts, but the intention is not to encode an explicit decomposition of the scene. Rather, we accept that existing object category classifiers often encode not the category per se but ancillary image characteristics; and that these ancillary characteristics can combine to represent visual classes unrelated to the constituent categories' semantic meanings. The advantage of this descriptor is that it allows object-category queries to be made against image databases using efficient classifiers (efficient at test time) such as linear support vector machines, and allows these queries to be for novel categories. Even when the representation is reduced to 200 bytes per image, classification accuracy on object category recognition is comparable with the state of the art (36% versus 42%), but at orders of magnitude lower computational cost.

Visualizing Data using t-SNE

Abstract: We present a new technique called “t-SNE” that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map. The technique is a variation of Stochastic Neighbor Embedding (Hinton and Roweis, 2002) that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map. t-SNE is better than existing techniques at creating a single map that reveals structure at many different scales. This is particularly important for high-dimensional data that lie on several different, but related, low-dimensional manifolds, such as images of objects from multiple classes seen from multiple viewpoints. For visualizing the structure of very large datasets, we show how t-SNE can use random walks on neighborhood graphs to allow the implicit structure of all of the data to influence the way in which a subset of the data is displayed. We illustrate the performance of t-SNE on a wide variety of datasets and compare it with many other non-parametric visualization techniques, including Sammon mapping, Isomap, and Locally Linear Embedding. The visualizations produced by t-SNE are significantly better than those produced by the other techniques on almost all of the datasets.

Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

Abstract: This paper presents a method for recognizing scene categories based on approximate global geometric correspondence. This technique works by partitioning the image into increasingly fine sub-regions and computing histograms of local features found inside each sub-region. The resulting "spatial pyramid" is a simple and computationally efficient extension of an orderless bag-of-features image representation, and it shows significantly improved performance on challenging scene categorization tasks. Specifically, our proposed method exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories. The spatial pyramid framework also offers insights into the success of several recently proposed image descriptions, including Torralba’s "gist" and Lowe’s SIFT descriptors.

Learning Deep Architectures for AI

Abstract: Can machine learning deliver AI? Theoretical results, inspiration from the brain and cognition, as well as machine learning experiments suggest that in order to learn the kind of complicated functions that can represent high-level abstractions (e.g. in vision, language, and other AI-level tasks), one would need deep architectures. Deep architectures are composed of multiple levels of non-linear operations, such as in neural nets with many hidden layers, graphical models with many levels of latent variables, or in complicated propositional formulae re-using many sub-formulae. Each level of the architecture represents features at a different level of abstraction, defined as a composition of lower-level features. Searching the parameter space of deep architectures is a difficult task, but new algorithms have been discovered and a new sub-area has emerged in the machine learning community since 2006, following these discoveries. Learning algorithms such as those for Deep Belief Networks and other related unsupervised learning algorithms have recently been proposed to train deep architectures, yielding exciting results and beating the state-of-the-art in certain areas. Learning Deep Architectures for AI discusses the motivations for and principles of learning algorithms for deep architectures. By analyzing and comparing recent results with different learning algorithms for deep architectures, explanations for their success are proposed and discussed, highlighting challenges and suggesting avenues for future explorations in this area.

Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

Abstract: In this paper, we propose a computational model of the recognition of real world scenes that bypasses the segmentation and the processing of individual objects or regions. The procedure is based on a very low dimensional representation of the scene, that we term the Spatial Envelope. We propose a set of perceptual dimensions (naturalness, openness, roughness, expansion, ruggedness) that represent the dominant spatial structure of a scene. Then, we show that these dimensions may be reliably estimated using spectral and coarsely localized information. The model generates a multidimensional space in which scenes sharing membership in semantic categories (e.g., streets, highways, coasts) are projected closed together. The performance of the spatial envelope model shows that specific information about object shape or identity is not a requirement for scene categorization and that modeling a holistic representation of the scene informs about its probable semantic category.

Learning with Local and Global Consistency

Abstract: We consider the general problem of learning from labeled and unlabeled data, which is often called semi-supervised learning or transductive inference. A principled approach to semi-supervised learning is to design a classifying function which is sufficiently smooth with respect to the intrinsic structure collectively revealed by known labeled and unlabeled points. We present a simple algorithm to obtain such a smooth solution. Our method yields encouraging experimental results on a number of classification problems and demonstrates effective use of unlabeled data.