The notion of using context information for solving high-level vision and medical image segmentation problems has been increasingly realized in the field. However, how to learn an effective and efficient context model, together with an image appearance model, remains mostly unknown. The current literature using Markov Random Fields (MRFs) and Conditional Random Fields (CRFs) often involves specific algorithm design, in which the modeling and computing stages are studied in isolation. In this paper, we propose the auto-context algorithm. Given a set of training images and their corresponding label maps, we first learn a classifier on local image patches. The discriminative probability (or classification confidence) maps created by the learned classifier are then used as context information, in addition to the original image patches, to train a new classifier. The algorithm then iterates until convergence. Auto-context integrates low-level and context information by fusing a large number of low-level appearance features with context and implicit shape information. The resulting discriminative algorithm is general and easy to implement. Under nearly the same parameter settings in training, we apply the algorithm to three challenging vision applications: foreground/background segregation, human body configuration estimation, and scene region labeling. Moreover, context also plays a very important role in medical/brain images where the anatomical structures are mostly constrained to relatively fixed positions. With only some slight changes resulting from using 3D instead of 2D features, the auto-context algorithm applied to brain MRI image segmentation is shown to outperform state-of-the-art algorithms specifically designed for this domain. Furthermore, the scope of the proposed algorithm goes beyond image analysis and it has the potential to be used for a wide variety of problems in multi-variate labeling.

Abstract. The joint tasks of object recognition and object segmentation from a single image are complex in their requirement of not only correct classification, but also deciding exactly which pixels belong to the object. Exploring all possible pixel subsets is prohibitively expensive, leading to recent approaches which use unsupervised image segmentation to reduce the size of the configuration space. Image segmentation, however, is known to be unstable, strongly affected by small image perturbations, feature choices, or different segmentation algorithms. This instability has led to advocacy for using multiple segmentations of an image. In this paper, we explore the question of how to best integrate the information from multiple bottom-up segmentations of an image to improve object recognition robustness. By integrating the image partition hypotheses in an intuitive combined top-down and bottom-up recognition approach, we improve object and feature support. We further explore possible extensions of our method and whether they provide improved performance. Results are presented on the MSRC 21-class data set and the Pascal VOC2007 object segmentation challenge. 1

Traditionally, object recognition is performed based solely on the appearance of the object. However, relevant information also exists in the scene surrounding the object. As supported by our human studies, this contextual information is necessary for accurate recognition in low resolution images. This scenario with impoverished appearance information, as opposed to using images of higher resolution, provides an appropriate venue for studying the role of context in recognition. In this paper, we explore the role of context for dense scene labeling in small images. Given a segmentation of an image, our algorithm assigns each segment to an object category based on the segment’s appearance and contextual information. We explicitly model context between object categories through the use of relative location and relative scale, in addition to co-occurrence. We perform recognition tests on low and high resolution images, which vary significantly in the amount of appearance information present, using just the object appearance information, the combination of appearance and context, as well as just context without object appearance information (blind recognition). We also perform these tests in human studies and analyze our findings to reveal interesting patterns. With the use of our context model, our algorithm achieves state-of-the-art performance on MSRC and Corel. datasets.

In recent years, the language model Latent Dirichlet Allocation (LDA), which clusters co-occurring words into topics, has been widely applied in the computer vision field. However, many of these applications have difficulty with modeling the spatial and temporal structure among visual words, since LDA assumes that a document is a “bag-of-words”. It is also critical to properly design “words ” and “documents ” when using a language model to solve vision problems. In this paper, we propose a topic model Spatial Latent Dirichlet Allocation (SLDA), which better encodes spatial structures among visual words that are essential for solving many vision problems. The spatial information is not encoded in the values of visual words but in the design of documents. Instead of knowing the partition of words into documents a priori, the word-document assignment becomes a random hidden variable in SLDA. There is a generative procedure, where knowledge of spatial structure can be flexibly added as a prior, grouping visual words which are close in space into the same document. We use SLDA to discover objects from a collection of images, and show it achieves better performance than LDA. 1

We consider two scenarios of naming people in databases of news photos with captions: (i) finding faces of a single person, and (ii) assigning names to all faces. We combine an initial text-based step, that restricts the name assigned to a face to the set of names appearing in the caption, with a second step that analyzes visual features of faces. By searching for groups of highly similar faces that can be associated with a name, the results of purely text-based search can be greatly ameliorated. We improve a recent graph-based approach, in which nodes correspond to faces and edges connect highly similar faces. We introduce constraints when optimizing the objective function, and propose improvements in the low-level methods used to construct the graphs. Furthermore, we generalize the graph-based approach to face naming in the full data set. In this multi-person naming case the optimization quickly becomes computationally demanding, and we present an important speed-up using graph-flows to compute the optimal name assignments in documents. Generative models have previously been proposed to solve the multi-person naming task. We compare the generative and graph-based methods in both scenarios, and find significantly better performance using the graph-based methods in both cases. 1.

Object models based on bag-of-words representations can achieve state-of-the-art performance for image classification and object localization tasks. However, as they consider objects as loose collections of local patches they fail to accurately locate object boundaries and are not able to produce accurate object segmentation. On the other hand, Markov Random Field models used for image segmentation focus on object boundaries but can hardly use the global constraints necessary to deal with object categories whose appearance may vary significantly. In this paper we combine the advantages of both approaches. First, a mechanism based on local regions allows object detection using visual word occurrences and produces a rough image segmentation. Then, a MRF component gives clean boundaries and enforces label consistency, guided by local image cues (color, texture and edge cues) and by long-distance dependencies. Gibbs sampling is used to infer the model. The proposed method successfully segments object categories with highly varying appearances in the presence of cluttered backgrounds and large view point changes. We show that it outperforms published results on the Pascal VOC 2007 dataset. Figure 1. Instances of object categories are localized in images (col 1), producing masks (col 2) that can be used to automatically extract objects (col 3). The proposed method automatically produces these segmentation masks without any user interaction. 1.

Spectral clustering and eigenvector-based methods have become increasingly popular in segmentation and recognition. Although the choice of the pairwise similarity metric (or affinities) greatly influences the quality of the results, this choice is typically specified outside the learning framework. In this paper, we present an algorithm to learn class-specific similarity functions. Mapping our problem in a Conditional Random Fields (CRF) framework enables us to pose the task of learning affinities as parameter learning in undirected graphical models. There are two significant advances over previous work. First, we learn the affinity between a pair of data-points as a function of a pairwise feature and (in contrast with previous approaches) the classes to which these two data-points were mapped, allowing us to work with a richer class of affinities. Second, our formulation provides a principled probabilistic interpretation for learning all of the parameters that define these affinities. Using ground truth segmentations and labellings for training, we learn the parameters with the greatest discriminative power (in an MLE sense) on the training data. We demonstrate the power of this learning algorithm in the setting of joint segmentation and recognition of object classes. Specifically, even with very simple appearance features, the proposed method achieves state-of-the-art performance on standard datasets. 1.

This paper presents a nonparametric approach to labeling of local image regions that is inspired by recent developments in information-theoretic denoising. The chief novelty of this approach rests in its ability to derive an unsupervised contextual prior over image classes from unlabeled test data. Labeled training data is needed only to learn a local appearance model for image patches (although additional supervisory information can optionally be incorporated when it is available). Instead of assuming a parametric prior such as a Markov random field for the class labels, the proposed approach uses the empirical Bayes technique of statistical inversion to recover a contextual model directly from the test data, either as a spatially varying or as a globally constant prior distribution over the classes in the image. Results on two challenging datasets convincingly demonstrate that useful contextual information can indeed be learned from unlabeled data. 1.

Abstract. In this paper we are interested in finding images of people on the web, and more specifically within large databases of captioned news images. It has recently been shown that visual analysis of the faces in images returned on a text-based query over captions can significantly improve search results. The underlying idea to improve the text-based results is that although this initial result is imperfect, it will render the queried person to be relatively frequent as compared to other people, so we can search for a large group of highly similar faces. The performance of such methods depends strongly on this assumption: for people whose face appears in less than about 40 % of the initial text-based result, the performance may be very poor. The contribution of this paper is to improve search results by exploiting faces of other people that co-occur frequently with the queried person. We refer to this process as ‘query expansion’. In the face analysis we use the query expansion to provide a query-specific relevant set of ‘negative’ examples which should be separated from the potentially positive examples in the text-based result set. We apply this idea to a recently-proposed method which filters the initial result set using a Gaussian mixture model, and apply the same idea using a logistic discriminant model. We experimentally evaluate the methods using a set of 23 queries on a database of 15.000 captioned news stories from Yahoo! News. The results show that (i) query expansion improves both methods, (ii) that our discriminative models outperform the generative ones, and (iii) our best results surpass the state-of-the-art results by 10 % precision on average. 1

Conditional Random Fields (CRFs) are an effective tool for a variety of different data segmentation and labeling tasks including visual scene interpretation, which seeks to partition images into their constituent semantic-level regions and assign appropriate class labels to each region. For accurate labeling it is important to capture the global context of the image as well as local information. We introduce a CRF based scene labeling model that incorporates both local features and features aggregated over the whole image or large sections of it. Secondly, traditional CRF learning requires fully labeled datasets which can be costly and troublesome to produce. We introduce a method for learning CRFs from datasets with many unlabeled nodes by marginalizing out the unknown labels so that the log-likelihood of the known ones can be maximized by gradient ascent. Loopy Belief Propagation is used to approximate the marginals needed for the gradient and log-likelihood calculations and the Bethe free-energy approximation to the log-likelihood is monitored to control the step size. Our experimental results show that effective models can be learned from fragmentary labelings and that incorporating top-down aggregate features significantly improves the segmentations. The resulting segmentations are compared to the state-of-the-art on three different image datasets. 1