ICCV 2015 论文列表

This paper addresses semantic image segmentation by incorporating rich information into Markov Random Field (MRF), including high-order relations and mixture of label contexts. Unlike previous works that optimized MRFs using iterative algorithm, we solve MRF by proposing a Convolutional Neural Network (CNN), namely Deep Parsing Network (DPN), which enables deterministic end-to-end computation in a single forward pass. Specifically, DPN extends a contemporary CNN architecture to model unary terms and additional layers are carefully devised to approximate the mean field algorithm (MF) for pairwise terms. It has several appealing properties. First, different from the recent works that combined CNN and MRF, where many iterations of MF were required for each training image during back-propagation, DPN is able to achieve high performance by approximating one iteration of MF. Second, DPN represents various types of pairwise terms, making many existing works as its special cases. Third, DPN makes MF easier to be parallelized and speeded up in Graphical Processing Unit (GPU). DPN is thoroughly evaluated on the PASCAL VOC 2012 dataset, where a single DPN model yields a new state-of-the-art segmentation accuracy of 77.5%.

Unsupervised and weakly-supervised visual learning in large image collections are critical in order to avoid the time-consuming and error-prone process of manual labeling. Standard approaches rely on methods like multiple-instance learning or graphical models, which can be computationally intensive and sensitive to initialization. On the other hand, simpler component analysis or clustering methods usually cannot achieve meaningful invariances or semantic interpretability. To address the issues of previous work, we present a simple but effective method called Semantic Component Analysis (SCA), which provides a decomposition of images into semantic components. Unsupervised SCA decomposes additive image representations into spatially-meaningful visual components that naturally correspond to object categories. Using an overcomplete representation that allows for rich instance-level constraints and spatial priors, SCA gives improved results and more interpretable components in comparison to traditional matrix factorization techniques. If weakly-supervised information is available in the form of image-level tags, SCA factorizes a set of images into semantic groups of superpixels. We also provide qualitative connections to traditional methods for component analysis (e.g. Grassmann averages, PCA, and NMF). The effectiveness of our approach is validated through synthetic data and on the MSRC2 and Sift Flow datasets, demonstrating competitive results in unsupervised and weakly-supervised semantic segmentation.

We propose a method to detect disocclusion in video sequences of three-dimensional scenes and to partition the disoccluded regions into objects, defined by coherent deformation corresponding to surfaces in the scene. Our method infers deformation fields that are piecewise smooth by construction without the need for an explicit regularizer and the associated choice of weight. It then partitions the disoccluded region and groups its components with objects by leveraging on the complementarity of motion and appearance cues: Where appearance changes within an object, motion can usually be reliably inferred and used for grouping. Where appearance is close to constant, it can be used for grouping directly. We integrate both cues in an energy minimization framework, incorporate prior assumptions explicitly into the energy, and propose a numerical scheme.

Even high-quality lenses suffer from optical aberrations, especially when used at full aperture. Furthermore, there are significant lens-to-lens deviations due to manufacturing tolerances, often rendering current software solutions like DxO, Lightroom, and PTLens insufficient as they don't adapt and only include generic lens blur models. We propose a method that enables the self-calibration of lenses from a natural image, or a set of such images. To this end we develop a machine learning framework that is able to exploit several recorded images and distills the available information into an accurate model of the considered lens.

Most existing face verification systems rely on precise face detection and registration. However, these two components are fallible under unconstrained scenarios (e.g., mobile face authentication) due to partial occlusions, pose variations, lighting conditions and limited view-angle coverage of mobile cameras. We address the unconstrained face verification problem by encoding face images directly without any explicit models of detection or registration. We propose a selective encoding framework which injects relevance information (e.g., foreground/background probabilities) into each cluster of a descriptor codebook. An additional selector component also discards distractive image patches and improves spatial robustness. We evaluate our framework using Gaussian mixture models and Fisher vectors on challenging face verification datasets. We apply selective encoding to Fisher vector features, which in our experiments degrade quickly with inaccurate face localization; our framework improves robustness with no extra test time computation. We also apply our approach to mobile based active face authentication task, demonstrating its utility in real scenarios.

Complex event retrieval is a challenging research problem, especially when no training videos are available. An alternative to collecting training videos is to train a large semantic concept bank a priori. Given a text description of an event, event retrieval is performed by selecting concepts linguistically related to the event description and fusing the concept responses on unseen videos. However, defining an exhaustive concept lexicon and pre-training it requires vast computational resources. Therefore, recent approaches automate concept discovery and training by leveraging large amounts of weakly annotated web data. Compact visually salient concepts are automatically obtained by the use of concept pairs or, more generally, n-grams. However, not all visually salient n-grams are necessarily useful for an event query--some combinations of concepts may be visually compact but irrelevant--and this drastically affects performance. We propose an event retrieval algorithm that constructs pairs of automatically discovered concepts and then prunes those concepts that are unlikely to be helpful for retrieval. Pruning depends both on the query and on the specific video instance being evaluated. Our approach also addresses calibration and domain adaptation issues that arise when applying concept detectors to unseen videos. We demonstrate large improvements over other vision based systems on the TRECVID MED 13 dataset.

We introduce Segment-Phrase Table (SPT), a large collection of bijective associations between textual phrases and their corresponding segmentations. Leveraging recent progress in object recognition and natural language semantics, we show how we can successfully build a high-quality segment-phrase table using minimal human supervision. More importantly, we demonstrate the unique value unleashed by this rich bimodal resource, for both vision as well as natural language understanding. First, we show that fine-grained textual labels facilitate contextual reasoning that helps in satisfying semantic constraints across image segments. This feature enables us to achieve state-of-the-art segmentation results on benchmark datasets. Next, we show that the association of high-quality segmentations to textual phrases aids in richer semantic understanding and reasoning of these textual phrases. Leveraging this feature, we motivate the problem of visual entailment and visual paraphrasing, and demonstrate its utility on a large dataset.

In this paper, we design a new edge-aware structure, named segment graph, to represent the image and we further develop a novel double weighted average image filter (SGF) based on the segment graph. In our SGF, we use the tree distance on the segment graph to define the internal weight function of the filtering kernel, which enables the filter to smooth out high-contrast details and textures while preserving major image structures very well. While for the external weight function, we introduce a user specified smoothing window to balance the smoothing effects from each node of the segment graph. Moreover, we also set a threshold to adjust the edge-preserving performance. These advantages make the SGF more flexible in various applications and overcome the "halo" and "leak" problems appearing in most of the state-of-the-art approaches. Finally and importantly, we develop a linear algorithm for the implementation of our SGF, which has an O(N) time complexity for both gray-scale and high dimensional images, regardless of the kernel size and the intensity range. Typically, as one of the fastest edge-preserving filters, our CPU implementation achieves 0.15s per megapixel when performing filtering for 3-channel color images. The strength of the proposed filter is demonstrated by various applications, including stereo matching, optical flow, joint depth map upsampling, edge-preserving smoothing, edges detection, image abstraction and texture editing.

The Histogram of Oriented Gradient (HOG) descriptor has led to many advances in computer vision over the last decade and is still part of many state of the art approaches. We realize that the associated feature computation is piecewise differentiable and therefore many pipelines which build on HOG can be made differentiable. This lends to advanced introspection as well as opportunities for end-to-end optimization. We present our implementation of [?]HOG based on the auto-differentiation toolbox Chumpy and show applications to pre-image visualization and pose estimation which extends the existing differentiable renderer OpenDR pipeline. Both applications improve on the respective state-of-the-art HOG approaches.

Matrix factorization (or low-rank matrix completion) with missing data is a key computation in many computer vision and machine learning tasks, and is also related to a broader class of nonlinear optimization problems such as bundle adjustment. The problem has received much attention recently, with renewed interest in variable-projection approaches, yielding dramatic improvements in reliability and speed. However, on a wide class of problems, no one approach dominates, and because the various approaches have been derived in a multitude of different ways, it has been difficult to unify them. This paper provides a unified derivation of a number of recent approaches, so that similarities and differences are easily observed. We also present a simple meta-algorithm which wraps any existing algorithm, yielding 100% success rate on many standard datasets. Given 100% success, the focus of evaluation must turn to speed, as 100% success is trivially achieved if we do not care about speed. Again our unification allows a number of generic improvements applicable to all members of the family to be isolated, yielding a unified algorithm that outperforms our re-implementation of existing algorithms, which in some cases already outperform the original authors' publicly available codes.

The log-likelihood energy term in popular model-fitting segmentation methods, e.g. Zhu&Yuille, Chan-Vese, GrabCut, is presented as a generalized "probabilistic K-means" energy for color space clustering. This interpretation reveals some limitations, e.g. over-fitting. We propose an alternative approach to color clustering using kernel K-means energy with well-known properties such as non-linear separation and scalability to higher-dimensional feature spaces. Our bound formulation for kernel K-means allows to combine general pair-wise feature clustering methods with image grid regularization using graph cuts, similarly to standard color model fitting techniques for segmentation. Unlike histogram or GMM fitting, our approach is closely related to average association and normalized cut. But, in contrast to previous pairwise clustering algorithms, our approach can incorporate any standard geometric regularization in the image domain. We analyze extreme cases for kernel bandwidth (e.g. Gini bias) and demonstrate effectiveness of KNN-based adaptive bandwidth strategies. Our kernel K-means approach to segmentation benefits from higher-dimensional features where standard model fitting fails.

In this paper, we are interested in enhancing the expressivity and robustness of part-based models for object representation, in the common scenario where the training data are based on 2D images. To this end, we propose scene-domain active part models (SDAPM), which reconstruct and characterize the 3D geometric statistics between object's parts in 3D scene-domain by using 2D training data in the image-domain alone. And on top of this, we explicitly model and handle occlusions in SDAPM. Together with the developed learning and inference algorithms, such a model provides rich object descriptions, including 2D object and parts localization, 3D landmark shape and camera viewpoint, which offers an effective representation to various image understanding tasks, such as object and parts detection, 3D landmark shape and viewpoint estimation from images. Experiments on the above tasks show that SDAPM outperforms previous part-based models, and thus demonstrates the potential of the proposed technique.

This paper contributes a new high quality dataset for person re-identification, named "Market-1501". Generally, current datasets: 1) are limited in scale; 2) consist of hand-drawn bboxes, which are unavailable under realistic settings; 3) have only one ground truth and one query image for each identity (close environment). To tackle these problems, the proposed Market-1501 dataset is featured in three aspects. First, it contains over 32,000 annotated bboxes, plus a distractor set of over 500K images, making it the largest person re-id dataset to date. Second, images in Market-1501 dataset are produced using the Deformable Part Model (DPM) as pedestrian detector. Third, our dataset is collected in an open system, where each identity has multiple images under each camera. As a minor contribution, inspired by recent advances in large-scale image search, this paper proposes an unsupervised Bag-of-Words descriptor. We view person re-identification as a special task of image search. In experiment, we show that the proposed descriptor yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large-scale 500k dataset.

We propose a novel algorithm for the task of supervised discriminative distance learning by nonlinearly embedding vectors into a low dimensional Euclidean space. We work in the challenging setting where supervision is with constraints on similar and dissimilar pairs while training. The proposed method is derived by an approximate kernelization of a linear Mahalanobis-like distance metric learning algorithm and can also be seen as a kernel neural network. The number of model parameters and test time evaluation complexity of the proposed method are O(dD) where D is the dimensionality of the input features and d is the dimension of the projection space -- this is in contrast to the usual kernelization methods as, unlike them, the complexity does not scale linearly with the number of training examples. We propose a stochastic gradient based learning algorithm which makes the method scalable (w.r.t. the number of training examples), while being nonlinear. We train the method with up to half a million training pairs of 4096 dimensional CNN features. We give empirical comparisons with relevant baselines on seven challenging datasets for the task of low dimensional semantic category based image retrieval.

Markov random fields are widely used to model many computer vision problems that can be cast in an energy minimization framework composed of unary and pairwise potentials. While computationally tractable discrete optimizers such as Graph Cuts and belief propagation (BP) exist for multi-label discrete problems, they still face prohibitively high computational challenges when the labels reside in a huge or very densely sampled space. Integrating key ideas from PatchMatch of effective particle propagation and resampling, PatchMatch belief propagation (PMBP) has been demonstrated to have good performance in addressing continuous labeling problems and runs orders of magnitude faster than Particle BP (PBP). However, the quality of the PMBP solution is tightly coupled with the local window size, over which the raw data cost is aggregated to mitigate ambiguity in the data constraint. This dependency heavily influences the overall complexity, increasing linearly with the window size. This paper proposes a novel algorithm called sped-up PMBP (SPM-BP) to tackle this critical computational bottleneck and speeds up PMBP by 50-100 times. The crux of SPM-BP is on unifying efficient filter-based cost aggregation and message passing with PatchMatch-based particle generation in a highly effective way. Though simple in its formulation, SPM-BP achieves superior performance for sub-pixel accurate stereo and optical-flow on benchmark datasets when compared with more complex and task-specific approaches.

A simple yet effective object descriptor for visual tracking is proposed in this paper. We first decompose the bounding box of a target object into multiple patches, which are described by color and gradient histograms. Then, we concatenate the features of the spatially ordered patches to represent the object appearance. Moreover, to alleviate the impacts of background information possibly included in the bounding box, we determine patch weights using random walk with restart (RWR) simulations. The patch weights represent the importance of each patch in the description of foreground information, and are used to construct an object descriptor, called spatially ordered and weighted patch (SOWP) descriptor. We incorporate the proposed SOWP descriptor into the structured output tracking framework. Experimental results demonstrate that the proposed algorithm yields significantly better performance than the state-of-the-art trackers on a recent benchmark dataset, and also excels in another recent benchmark dataset.

Saliency in Context (SALICON) is an ongoing effort that aims at understanding and predicting visual attention. Conventional saliency models typically rely on low-level image statistics to predict human fixations. While these models perform significantly better than chance, there is still a large gap between model prediction and human behavior. This gap is largely due to the limited capability of models in predicting eye fixations with strong semantic content, the so-called semantic gap. This paper presents a focused study to narrow the semantic gap with an architecture based on Deep Neural Network (DNN). It leverages the representational power of high-level semantics encoded in DNNs pretrained for object recognition. Two key components are fine-tuning the DNNs fully convolutionally with an objective function based on the saliency evaluation metrics, and integrating information at different image scales. We compare our method with 14 saliency models on 6 public eye tracking benchmark datasets. Results demonstrate that our DNNs can automatically learn features particularly for saliency prediction that surpass by a big margin the state-of-the-art. In addition, our model ranks top to date under all seven metrics on the MIT300 challenge set.

Classical multi-image super-resolution (SR) algorithms, designed for CCD cameras, assume that the motion among the images is global. But CMOS sensors that have increasingly started to replace their more expensive CCD counterparts in many applications do not respect this assumption if there is a motion of the camera relative to the scene during the exposure duration of an image because of the row-wise acquisition mechanism. In this paper, we study the hitherto unexplored topic of multi-image SR in CMOS cameras. We initially develop an SR observation model that accounts for the row-wise distortions called the ``rolling shutter'' (RS) effect observed in images captured using non-stationary CMOS cameras. We then propose a unified RS-SR framework to obtain an RS-free high-resolution image (and the row-wise motion) from distorted low-resolution images. We demonstrate the efficacy of the proposed scheme using synthetic data as well as real images captured using a hand-held CMOS camera. Quantitative and qualitative assessments reveal that our method significantly advances the state-of-the-art.

This paper deals with the problem of registering a known structured 3D scene and its metric Structure-from-Motion (SfM) counterpart. The proposed work relies on a prior plane segmentation of the 3D scene and aligns the data obtained from both modalities by solving the point-to-plane assignment problem. An inliers-maximization approach within a Branch-and-Bound (BnB) search scheme is adopted. For the first time in this paper, a Sum-of-Squares optimization theory framework is employed for identifying point-to-plane mismatches (i.e. outliers) with certainty. This allows us to iteratively build potential inliers sets and converge to the solution satisfied by the largest number of point-to-plane assignments. Furthermore, our approach is boosted by new plane visibility conditions which are also introduced in this paper. Using this framework, we solve the registration problem in two cases: (i) a set of putative point-to-plane correspondences (with possibly overwhelmingly many outliers) is given as input and (ii) no initial correspondences are given. In both cases, our approach yields outstanding results in terms of robustness and optimality.