arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 1,063 records · Page 59Linked to original sources

arXiv2017

Unsupervised Learning Layers for Video Analysis

This paper presents two unsupervised learning layers (UL layers) for label-free video analysis: one for fully connected layers, and the other for convolutional ones. The proposed UL layers can play two roles: they can be the cost function layer for providing global training signal; meanwhile they can be added to any regular neural network layers for providing local training signals and combined with the training signals backpropagated from upper layers for extracting both slow and fast changing features at layers of different depths. Therefore, the UL layers can be used in either pure unsupervised or semi-supervised settings. Both a closed-form solution and an online learning algorithm for two UL layers are provided. Experiments with unlabeled synthetic and real-world videos demonstrated that the neural networks equipped with UL layers and trained with the proposed online learning algorithm can extract shape and motion information from video sequences of moving objects. The experiments demonstrated the potential applications of UL layers and online learning algorithm to head orientation estimation and moving object localization.

cs.LG↗

arXiv2017

SIFT Meets CNN: A Decade Survey of Instance Retrieval

In the early days, content-based image retrieval (CBIR) was studied with global features. Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively studied for over a decade due to the advantage of SIFT in dealing with image transformations. Recently, image representations based on the convolutional neural network (CNN) have attracted increasing interest in the community and demonstrated impressive performance. Given this time of rapid evolution, this article provides a comprehensive survey of instance retrieval over the last decade. Two broad categories, SIFT-based and CNN-based methods, are presented. For the former, according to the codebook size, we organize the literature into using large/medium-sized/small codebooks. For the latter, we discuss three lines of methods, i.e., using pre-trained or fine-tuned CNN models, and hybrid methods. The first two perform a single-pass of an image to the network, while the last category employs a patch-based feature extraction scheme. This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods. After analyzing and comparing retrieval performance of different categories on several datasets, we discuss promising directions towards generic and specialized instance retrieval.

cs.CV↗

arXiv2017

Universal Behaviors of Speed of Sound from Holography

We investigate the speed of sound in $(d+1)$-dimensional field theory by studying its dual $(d+2)$-dimensional gravity theory from gauge/gravity correspondence. Instead of the well known conformal limit $c_s^2 \rightarrow 1/d$ at high temperature, we reveal two more universal quantities in various limits: $c_s^2 \rightarrow (d-1)/16π$ at low temperature and $c_s^2 \rightarrow (d-1)/16πd$ at large chemical potential.

hep-th↗

arXiv2017

More is Less: A More Complicated Network with Less Inference Complexity

In this paper, we present a novel and general network structure towards accelerating the inference process of convolutional neural networks, which is more complicated in network structure yet with less inference complexity. The core idea is to equip each original convolutional layer with another low-cost collaborative layer (LCCL), and the element-wise multiplication of the ReLU outputs of these two parallel layers produces the layer-wise output. The combined layer is potentially more discriminative than the original convolutional layer, and its inference is faster for two reasons: 1) the zero cells of the LCCL feature maps will remain zero after element-wise multiplication, and thus it is safe to skip the calculation of the corresponding high-cost convolution in the original convolutional layer, 2) LCCL is very fast if it is implemented as a 1*1 convolution or only a single filter shared by all channels. Extensive experiments on the CIFAR-10, CIFAR-100 and ILSCRC-2012 benchmarks show that our proposed network structure can accelerate the inference process by 32\% on average with negligible performance drop.

cs.CV↗

arXiv2017

GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data

Object Transfiguration replaces an object in an image with another object from a second image. For example it can perform tasks like "putting exactly those eyeglasses from image A on the nose of the person in image B". Usage of exemplar images allows more precise specification of desired modifications and improves the diversity of conditional image generation. However, previous methods that rely on feature space operations, require paired data and/or appearance models for training or disentangling objects from background. In this work, we propose a model that can learn object transfiguration from two unpaired sets of images: one set containing images that "have" that kind of object, and the other set being the opposite, with the mild constraint that the objects be located approximately at the same place. For example, the training data can be one set of reference face images that have eyeglasses, and another set of images that have not, both of which spatially aligned by face landmarks. Despite the weak 0/1 labels, our model can learn an "eyeglasses" subspace that contain multiple representatives of different types of glasses. Consequently, we can perform fine-grained control of generated images, like swapping the glasses in two images by swapping the projected components in the "eyeglasses" subspace, to create novel images of people wearing eyeglasses. Overall, our deterministic generative model learns disentangled attribute subspaces from weakly labeled data by adversarial training. Experiments on CelebA and Multi-PIE datasets validate the effectiveness of the proposed model on real world data, in generating images with specified eyeglasses, smiling, hair styles, and lighting conditions etc. The code is available online.

cs.CV↗

arXiv2017

Performance Assessment of High-dimensional Variable Identification

Since model selection is ubiquitous in data analysis, reproducibility of statistical results demands a serious evaluation of reliability of the employed model selection method, no matter what label it may have in terms of good properties. Instability measures have been proposed for evaluating model selection uncertainty. However, low instability does not necessarily indicate that the selected model is trustworthy, since low instability can also arise when a certain method tends to select an overly parsimonious model. F- and G-measures have become increasingly popular for assessing variable selection performance in theoretical studies and simulation results. However, they are not computable in practice. In this work, we propose an estimation method for F- and G-measures and prove their desirable properties of uniform consistency. This gives the data analyst a valuable tool to compare different variable selection methods based on the data at hand. Extensive simulations are conducted to show the very good finite sample performance of our approach. We further demonstrate the application of our methods using several micro-array gene expression data sets, with intriguing findings.

stat.ME↗

arXiv2017

Optical Sky Brightness and Transparency During the Winter Season at Dome A Antarctica From the Gattini-Allsky Camera

The summit of the Antarctic plateau, Dome A, is proving to be an excellent site for optical, NIR, and THz astronomical observations. GATTINI was a wide-field camera installed on the PLATO instrument module as part of the Chinese-led traverse to Dome A in January, 2009. We present here the measurements of sky brightness with the Gattini ultra-large field of view (90 deg x 90 deg) in the photometric B-, V-, and R-bands, cloud cover statistics measured during the 2009 winter season, and an estimate of the sky transparency. A cumulative probability distribution indicates that the darkest 10% of the nights at Dome A have sky brightness of S_B = 22.98, S_V = 21.86, and S_R = 21.68 mag arcsec^{-2}. These values were obtained around the year 2009 with minimum aurora, and they are comparable to the faintest sky brightness at Mauna Kea and the best sites of northern Chile. Since every filter includes strong auroral lines that effectively contaminate the sky brightness measurements, for instruments working around the auroral lines, either with custom filters or with high spectral resolution instruments, these values could be easily obtained on a more routine basis. In addition, we present example light curves for bright targets to emphasize the unprecedented observational window function available from this ground-based site. These light curves will be published in a future paper.

astro-ph.IM↗

arXiv2017

Long-Term Identity-Aware Multi-Person Tracking for Surveillance Video Summarization

Multi-person tracking plays a critical role in the analysis of surveillance video. However, most existing work focus on shorter-term (e.g. minute-long or hour-long) video sequences. Therefore, we propose a multi-person tracking algorithm for very long-term (e.g. month-long) multi-camera surveillance scenarios. Long-term tracking is challenging because 1) the apparel/appearance of the same person will vary greatly over multiple days and 2) a person will leave and re-enter the scene numerous times. To tackle these challenges, we leverage face recognition information, which is robust to apparel change, to automatically reinitialize our tracker over multiple days of recordings. Unfortunately, recognized faces are unavailable oftentimes. Therefore, our tracker propagates identity information to frames without recognized faces by uncovering the appearance and spatial manifold formed by person detections. We tested our algorithm on a 23-day 15-camera data set (4,935 hours total), and we were able to localize a person 53.2% of the time with 69.8% precision. We further performed video summarization experiments based on our tracking output. Results on 116.25 hours of video showed that we were able to generate a reasonable visual diary (i.e. a summary of what a person did) for different people, thus potentially opening the door to automatic summarization of the vast amount of surveillance video generated every day.

cs.CV↗

arXiv2017

The shadow knows: using shadows to investigate the structure of the pretransitional disk of HD 100453

We present GPI polarized intensity imagery of HD 100453 in Y-, J-, and K1 bands which reveals an inner gap ($9 - 18$ au), an outer disk ($18-39$ au) with two prominent spiral arms, and two azimuthally-localized dark features also present in SPHERE total intensity images (Wagner 2015). SED fitting further suggests the radial gap extends to $1$ au. The narrow, wedge-like shape of the dark features appears similar to predictions of shadows cast by a inner disk which is misaligned with respect to the outer disk. Using the Monte Carlo radiative transfer code HOCHUNCK3D (Whitney 2013), we construct a model of the disk which allows us to determine its physical properties in more detail. From the angular separation of the features we measure the difference in inclination between the disks 45$^{\circ}$, and their major axes, PA = 140$^{\circ}$ east of north for the outer disk and 100$^{\circ}$for the inner disk. We find an outer disk inclination of $25 \pm 10^{\circ}$ from face-on in broad agreement with the Wagner 2015 measurement of 34$^{\circ}$. SPHERE data in J- and H-bands indicate a reddish disk which points to HD 100453 evolving into a young debris disk.

astro-ph.EP↗

arXiv2017

Person Re-identification in the Wild

We present a novel large-scale dataset and comprehensive baselines for end-to-end pedestrian detection and person recognition in raw video frames. Our baselines address three issues: the performance of various combinations of detectors and recognizers, mechanisms for pedestrian detection to help improve overall re-identification accuracy and assessing the effectiveness of different detectors for re-identification. We make three distinct contributions. First, a new dataset, PRW, is introduced to evaluate Person Re-identification in the Wild, using videos acquired through six synchronized cameras. It contains 932 identities and 11,816 frames in which pedestrians are annotated with their bounding box positions and identities. Extensive benchmarking results are presented on this dataset. Second, we show that pedestrian detection aids re-identification through two simple yet effective improvements: a discriminatively trained ID-discriminative Embedding (IDE) in the person subspace using convolutional neural network (CNN) features and a Confidence Weighted Similarity (CWS) metric that incorporates detection scores into similarity measurement. Third, we derive insights in evaluating detector performance for the particular scenario of accurate person re-identification.

cs.CV↗

arXiv2017

Accelerating Deep Neural Network Training with Inconsistent Stochastic Gradient Descent

SGD is the widely adopted method to train CNN. Conceptually it approximates the population with a randomly sampled batch; then it evenly trains batches by conducting a gradient update on every batch in an epoch. In this paper, we demonstrate Sampling Bias, Intrinsic Image Difference and Fixed Cycle Pseudo Random Sampling differentiate batches in training, which then affect learning speeds on them. Because of this, the unbiased treatment of batches involved in SGD creates improper load balancing. To address this issue, we present Inconsistent Stochastic Gradient Descent (ISGD) to dynamically vary training effort according to learning statuses on batches. Specifically ISGD leverages techniques in Statistical Process Control to identify a undertrained batch. Once a batch is undertrained, ISGD solves a new subproblem, a chasing logic plus a conservative constraint, to accelerate the training on the batch while avoid drastic parameter changes. Extensive experiments on a variety of datasets demonstrate ISGD converges faster than SGD. In training AlexNet, ISGD is 21.05\% faster than SGD to reach 56\% top1 accuracy under the exactly same experiment setup. We also extend ISGD to work on multiGPU or heterogeneous distributed system based on data parallelism, enabling the batch size to be the key to scalability. Then we present the study of ISGD batch size to the learning rate, parallelism, synchronization cost, system saturation and scalability. We conclude the optimal ISGD batch size is machine dependent. Various experiments on a multiGPU system validate our claim. In particular, ISGD trains AlexNet to 56.3% top1 and 80.1% top5 accuracy in 11.5 hours with 4 NVIDIA TITAN X at the batch size of 1536.

cs.LG↗

arXiv2017

Reactive infiltration instability amplifies the difference between geometric and reactive surface areas in natural porous materials

Reactive infiltration instability (RII) drives the development of many natural and engineered flow systems. These are encountered e.g. in hydraulic fracturing, geologic carbon storage and well stimulation in enhanced oil recovery. The surface area of the rocks changes as the pore structure evolves. We combined a reactor network model with grey scale tomography to seek the morphological interpretation for differences among geometric, reactive and apparent surface areas of dissolving natural porous materials. The approach allowed us to delineate the experimentally convoluted variables and study independently the effects of initial geometry and macroscopic flowrate. Simulations based on North Sea chalk microstructure showed that geometric surface not only serves as the interface for water-rock interactions but also represents the regional transport heterogeneities that can be amplified indefinitely by dissolutive percolation. Hence, RII leads to channelization of the solid matrix, which results in fluid focusing and an increase in geometric surface area. Fluid focusing reduces the reactive surface area and the residence time of reactants, both of which amplify the differences in question, i.e. they are self-supporting. Our results also suggested that the growing and merging of microchannels near the fluid entrance leads to the macroscopic "fast initial dissolution" of chemically homogeneous materials.

physics.geo-ph↗

arXiv2017

Dissolved CO2 stabilizes dissolution front and increases breakthrough porosity of natural porous materials

When reactive fluids flow through a dissolving porous medium, conductive channels form, leading to fluid breakthrough. This phenomenon is important in geologic carbon storage, where the dissolution of CO2 in water increases the acidity and produce microstructures significantly different from those in an intact reservoir. We demonstrate the controlling mechanism for the dissolution patterns in natural porous materials. This was done using numerical simulations based on high resolution digital models of North Sea chalk. We tested three model scenarios, and found that aqueous CO2 dissolve porous media homogeneously, leading to large breakthrough porosity. In contrast, CO2-free solution develops elongated convective channels in porous media, known as wormholes, and resulting in small breakthrough porosity. We further show that a homogeneous dissolution pattern appears because the sample size is smaller than the theoretical size of a developing wormhole. The result indicates that the presence of dissolved CO2 expands the reactive subvolume of a porous medium, and thus enhances the geochemical alteration of reservoir structures and might undermine the sealing integrity of caprocks when minerals dissolve.

physics.geo-ph↗

arXiv2017

Retraction of dissolution front in natural porous media

The dissolution of porous materials in a flow field shapes the morphologies of many geologic landscapes. Identifying the dissolution front, the interface between the reactive and the unreactive regions in a dissolving medium, is a prerequisite for studying dissolution kinetics. Despite its fundamental importance, the dynamics of a dissolution front in an evolving natural microstructure has never been reported. Here we show an unexpected spontaneous migration of the dissolution front against the pressure gradient of a flow field. This retraction stems from the infiltration instability induced surface generation, which can lead to a reactive surface dramatically greater than the ex situ geometric surface. The results are supported by a very good agreement between observations made with real time X-ray imaging and simulations based on static images of a rock determined by nanoCT. They both show that the in situ specific surface area of natural porous media is dependent on the flow field and reflects a balancing between surface generation and destruction. The reported dynamics challenge many long-held understanding of water-rock interactions and shed light on reconciling the discrepancies between field and laboratory measurements of reaction kinetics.

physics.geo-ph↗

arXiv2017

Approaching Confinement Structure for Light Quarks in a Holographic Soft Wall QCD Model

We study confinement-deconfinement phase transition in a holographic soft-wall QCD model. By solving the Einstein-Maxwell-scalar system analytically, we obtain the phase structure of the black hole backgrounds. We then impose probe open strings in such background to investigate the confinement-deconfinement phase transition from different open string configurations under various temperatures and chemical potentials. Furthermore, we study the Wilson loop by calculating the minimal surface of the probing open string world-sheet and obtain the Cornell potential in confinement phase analytically.

hep-th↗

arXiv2017

Temporal pattern of entropy production induced by reactive infiltration instability in natural porous media

The tendency of irreversible processes to generate entropy is the ultimate driving force for the evolution of nature. In engineering, entropy production is often used as a measure of usable energy losses. In this study we show that the analysis of the entropy production patterns can help understand the vastly diversified experimental observations of water-rock interactions in natural porous media. We first present a numerical scheme for the analysis of entropy production in dissolving porous media. Our scheme uses a greyscale digital model of natural chalk obtained by X-ray nanotomography. Greyscale models preserve structural heterogeneities with very high fidelity, which is essential for simulating a system dominated by infiltration instability. We focus on the coupling between two types of entropy production: the percolative entropy generated by dissipating the kinetic energy of fluid flow and the reactive entropy that originates from the consumption of chemical free energy. Their temporal patterns pinpoint three stages of microstructural evolution. We then show that the regional mixing deteriorates infiltration instability by reducing local variations in reactant distribution. In addition, we show that the microstructural evolution can be particularly sensitive to the initially present transport heterogeneities when the global flowrate is small. This dependence on flowrate indicates that the need to resolve the structural features of a porous system is greater when the residence time of the fluid is long.

physics.geo-ph↗

arXiv2017

An End-to-End Approach to Natural Language Object Retrieval via Context-Aware Deep Reinforcement Learning

We propose an end-to-end approach to the natural language object retrieval task, which localizes an object within an image according to a natural language description, i.e., referring expression. Previous works divide this problem into two independent stages: first, compute region proposals from the image without the exploration of the language description; second, score the object proposals with regard to the referring expression and choose the top-ranked proposals. The object proposals are generated independently from the referring expression, which makes the proposal generation redundant and even irrelevant to the referred object. In this work, we train an agent with deep reinforcement learning, which learns to move and reshape a bounding box to localize the object according to the referring expression. We incorporate both the spatial and temporal context information into the training procedure. By simultaneously exploiting local visual information, the spatial and temporal context and the referring language a priori, the agent selects an appropriate action to take at each time. A special action is defined to indicate when the agent finds the referred object, and terminate the procedure. We evaluate our model on various datasets, and our algorithm significantly outperforms the compared algorithms. Notably, the accuracy improvement of our method over the recent method GroundeR and SCRC on the ReferItGame dataset are 7.67% and 18.25%, respectively.

cs.CV↗

arXiv2017

Fully Convolutional Attention Networks for Fine-Grained Recognition

Fine-grained recognition is challenging due to its subtle local inter-class differences versus large intra-class variations such as poses. A key to address this problem is to localize discriminative parts to extract pose-invariant features. However, ground-truth part annotations can be expensive to acquire. Moreover, it is hard to define parts for many fine-grained classes. This work introduces Fully Convolutional Attention Networks (FCANs), a reinforcement learning framework to optimally glimpse local discriminative regions adaptive to different fine-grained domains. Compared to previous methods, our approach enjoys three advantages: 1) the weakly-supervised reinforcement learning procedure requires no expensive part annotations; 2) the fully-convolutional architecture speeds up both training and testing; 3) the greedy reward strategy accelerates the convergence of the learning. We demonstrate the effectiveness of our method with extensive experiments on four challenging fine-grained benchmark datasets, including CUB-200-2011, Stanford Dogs, Stanford Cars and Food-101.

cs.CV↗