arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 1,009 records · Page 56Linked to original sources

arXiv2018

Optimal electro-mechanical control of the excitonic fine structures of droplet epitaxial quantum dots

The intrinsic fine structure splittings (FSSs) of the exciton states of semiconductor quantum dots (QDs) are known to be the major obstacle for realizing the QD-based entangled photon pair emitters. In this study, we present a theoretical and computational investigation of the excitonic fine structures of droplet-epitaxial (DE) GaAs/AlGaAs QDs under the electro-mechanical control of micro-machined piezoelectricity actuators. From the group theory analysis with numerical confirmation based on the developed exciton theory, we reveal the general principle for the optimal design of micro-machined actuators whose application on to an elongated QD can certainly suppress its FSS. We show that the use of two independently tuning stresses is sufficient to achieve the FSS-elimination but is not always necessary as widely deemed. The use of a single tuning stress to eliminate the FSS of an elongated QD is possible as long as the crystal structure of the actuator material is in coincidence with that of the QD. As a feasible example, we show that a {\it single} symmetric bi-axial stress naturally generated from the $(001)$ PMN-PT actuator can be used as a single tuning knob to make the full FSS-elimination for elongated DE GaAs QDs.

cond-mat.mes-hall↗

arXiv2018

A Unified Analysis of Stochastic Momentum Methods for Deep Learning

Stochastic momentum methods have been widely adopted in training deep neural networks. However, their theoretical analysis of convergence of the training objective and the generalization error for prediction is still under-explored. This paper aims to bridge the gap between practice and theory by analyzing the stochastic gradient (SG) method, and the stochastic momentum methods including two famous variants, i.e., the stochastic heavy-ball (SHB) method and the stochastic variant of Nesterov's accelerated gradient (SNAG) method. We propose a framework that unifies the three variants. We then derive the convergence rates of the norm of gradient for the non-convex optimization problem, and analyze the generalization performance through the uniform stability approach. Particularly, the convergence analysis of the training objective exhibits that SHB and SNAG have no advantage over SG. However, the stability analysis shows that the momentum term can improve the stability of the learned model and hence improve the generalization performance. These theoretical insights verify the common wisdom and are also corroborated by our empirical analysis on deep learning.

cs.LG↗

arXiv2018

Convolutional Neural Networks with Recurrent Neural Filters

We introduce a class of convolutional neural networks (CNNs) that utilize recurrent neural networks (RNNs) as convolution filters. A convolution filter is typically implemented as a linear affine transformation followed by a non-linear function, which fails to account for language compositionality. As a result, it limits the use of high-order filters that are often warranted for natural language processing tasks. In this work, we model convolution filters with RNNs that naturally capture compositionality and long-term dependencies in language. We show that simple CNN architectures equipped with recurrent neural filters (RNFs) achieve results that are on par with the best published ones on the Stanford Sentiment Treebank and two answer sentence selection datasets.

cs.CL↗

arXiv2018

Attentive Sequence to Sequence Translation for Localizing Clips of Interest by Natural Language Descriptions

We propose a novel attentive sequence to sequence translator (ASST) for clip localization in videos by natural language descriptions. We make two contributions. First, we propose a bi-directional Recurrent Neural Network (RNN) with a finely calibrated vision-language attentive mechanism to comprehensively understand the free-formed natural language descriptions. The RNN parses natural language descriptions in two directions, and the attentive model attends every meaningful word or phrase to each frame, thereby resulting in a more detailed understanding of video content and description semantics. Second, we design a hierarchical architecture for the network to jointly model language descriptions and video content. Given a video-description pair, the network generates a matrix representation, i.e., a sequence of vectors. Each vector in the matrix represents a video frame conditioned by the description. The 2D representation not only preserves the temporal dependencies of frames but also provides an effective way to perform frame-level video-language matching. The hierarchical architecture exploits video content with multiple granularities, ranging from subtle details to global context. Integration of the multiple granularities yields a robust representation for multi-level video-language abstraction. We validate the effectiveness of our ASST on two large-scale datasets. Our ASST outperforms the state-of-the-art by $4.28\%$ in Rank$@1$ on the DiDeMo dataset. On the Charades-STA dataset, we significantly improve the state-of-the-art by $13.41\%$ in Rank$@1,IoU=0.5$.

cs.CV↗

arXiv2018

Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks

This paper proposed a Soft Filter Pruning (SFP) method to accelerate the inference procedure of deep Convolutional Neural Networks (CNNs). Specifically, the proposed SFP enables the pruned filters to be updated when training the model after pruning. SFP has two advantages over previous works: (1) Larger model capacity. Updating previously pruned filters provides our approach with larger optimization space than fixing the filters to zero. Therefore, the network trained by our method has a larger model capacity to learn from the training data. (2) Less dependence on the pre-trained model. Large capacity enables SFP to train from scratch and prune the model simultaneously. In contrast, previous filter pruning methods should be conducted on the basis of the pre-trained model to guarantee their performance. Empirically, SFP from scratch outperforms the previous filter pruning methods. Moreover, our approach has been demonstrated effective for many advanced CNN architectures. Notably, on ILSCRC-2012, SFP reduces more than 42% FLOPs on ResNet-101 with even 0.2% top-5 accuracy improvement, which has advanced the state-of-the-art. Code is publicly available on GitHub: https://github.com/he-y/soft-filter-pruning

cs.CV↗

arXiv2018

Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization

In this paper, we make two contributions to unsupervised domain adaptation (UDA) using the convolutional neural network (CNN). First, our approach transfers knowledge in all the convolutional layers through attention alignment. Most previous methods align high-level representations, e.g., activations of the fully connected (FC) layers. In these methods, however, the convolutional layers which underpin critical low-level domain knowledge cannot be updated directly towards reducing domain discrepancy. Specifically, we assume that the discriminative regions in an image are relatively invariant to image style changes. Based on this assumption, we propose an attention alignment scheme on all the target convolutional layers to uncover the knowledge shared by the source domain. Second, we estimate the posterior label distribution of the unlabeled data for target network training. Previous methods, which iteratively update the pseudo labels by the target network and refine the target network by the updated pseudo labels, are vulnerable to label estimation errors. Instead, our approach uses category distribution to calculate the cross-entropy loss for training, thereby ameliorating the error accumulation of the estimated labels. The two contributions allow our approach to outperform the state-of-the-art methods by +2.6% on the Office-31 dataset.

cs.CV↗

arXiv2018

Decoupled Novel Object Captioner

Image captioning is a challenging task where the machine automatically describes an image by sentences or phrases. It often requires a large number of paired image-sentence annotations for training. However, a pre-trained captioning model can hardly be applied to a new domain in which some novel object categories exist, i.e., the objects and their description words are unseen during model training. To correctly caption the novel object, it requires professional human workers to annotate the images by sentences with the novel words. It is labor expensive and thus limits its usage in real-world applications. In this paper, we introduce the zero-shot novel object captioning task where the machine generates descriptions without extra sentences about the novel object. To tackle the challenging problem, we propose a Decoupled Novel Object Captioner (DNOC) framework that can fully decouple the language sequence model from the object descriptions. DNOC has two components. 1) A Sequence Model with the Placeholder (SM-P) generates a sentence containing placeholders. The placeholder represents an unseen novel object. Thus, the sequence model can be decoupled from the novel object descriptions. 2) A key-value object memory built upon the freely available detection model, contains the visual information and the corresponding word for each object. The SM-P will generate a query to retrieve the words from the object memory. The placeholder will then be filled with the correct word, resulting in a caption with novel object descriptions. The experimental results on the held-out MSCOCO dataset demonstrate the ability of DNOC in describing novel concepts in the zero-shot novel object captioning task.

cs.CV↗

arXiv2018

Self-produced Guidance for Weakly-supervised Object Localization

Weakly supervised methods usually generate localization results based on attention maps produced by classification networks. However, the attention maps exhibit the most discriminative parts of the object which are small and sparse. We propose to generate Self-produced Guidance (SPG) masks which separate the foreground, the object of interest, from the background to provide the classification networks with spatial correlation information of pixels. A stagewise approach is proposed to incorporate high confident object regions to learn the SPG masks. The high confident regions within attention maps are utilized to progressively learn the SPG masks. The masks are then used as an auxiliary pixel-level supervision to facilitate the training of classification networks. Extensive experiments on ILSVRC demonstrate that SPG is effective in producing high-quality object localizations maps. Particularly, the proposed SPG achieves the Top-1 localization error rate of 43.83% on the ILSVRC validation set, which is a new state-of-the-art error rate.

cs.CV↗

arXiv2018

Optical Observations of the Young Type Ic Supernova SN 2014L in M99

We present optical spectroscopic and photometric observations of the nearby type Ic supernova (SN Ic) SN 2014L. This SN was discovered by the Tsinghua-NAOC Transient Survey (TNTS) in the nearby type-Sc spiral galaxy M99 (NGC 4254). Fitting to the early-time light curve indicates that SN 2014L was detected at only a few hours after the shock breakout, and it reached a peak brightness of $M_{\rm V} = -17.73 \pm 0.28$ mag ($L= [2.06\pm 0.50] \times 10^{42}$ erg s$^{-1}$) approximately 13 days later. SN 2014L shows a close resemblance to SN 2007gr in the photometric evolution, while it shows stronger absorption features of intermediate-mass elements (especially \CaII) in the early-time spectra. Based on simple modeling of the observed light curves, we derived the mass of synthesized $^{56}$Ni as $M_{\rm Ni} = 0.075 \pm 0.025 M_{\odot}$, and the mass and total energy of the ejecta as $M_{\rm ej} = 1.00 \pm 0.20 M_\odot$ and $E_{\rm ej}=1.45\pm0.25$ foe, respectively. Given these typical explosion parameters, the early detection, and the extensive observations, we suggest that SN 2014L could be a template sample for the investigation of SNe Ic.

astro-ph.HE↗

arXiv2018

VIMCO: Variational Inference for Multiple Correlated Outcomes in Genome-wide Association Studies

In Genome-Wide Association Studies (GWAS) where multiple correlated traits have been measured on participants, a joint analysis strategy, whereby the traits are analyzed jointly, can improve statistical power over a single-trait analysis strategy. There are two questions of interest to be addressed when conducting a joint GWAS analysis with multiple traits. The first question examines whether a genetic loci is significantly associated with any of the traits being tested. The second question focuses on identifying the specific trait(s) that is associated with the genetic loci. Since existing methods primarily focus on the first question, this paper seeks to provide a complementary method that addresses the second question. We propose a novel method, Variational Inference for Multiple Correlated Outcomes (VIMCO), that focuses on identifying the specific trait that is associated with the genetic loci, when performing a joint GWAS analysis of multiple traits, while accounting for correlation among the multiple traits. We performed extensive numerical studies and also applied VIMCO to analyze two datasets. The numerical studies and real data analysis demonstrate that VIMCO improves statistical power over single-trait analysis strategies when the multiple traits are correlated and has comparable performance when the traits are not correlated.

stat.ME↗

arXiv2018

Macro-Micro Adversarial Network for Human Parsing

In human parsing, the pixel-wise classification loss has drawbacks in its low-level local inconsistency and high-level semantic inconsistency. The introduction of the adversarial network tackles the two problems using a single discriminator. However, the two types of parsing inconsistency are generated by distinct mechanisms, so it is difficult for a single discriminator to solve them both. To address the two kinds of inconsistencies, this paper proposes the Macro-Micro Adversarial Net (MMAN). It has two discriminators. One discriminator, Macro D, acts on the low-resolution label map and penalizes semantic inconsistency, e.g., misplaced body parts. The other discriminator, Micro D, focuses on multiple patches of the high-resolution label map to address the local inconsistency, e.g., blur and hole. Compared with traditional adversarial networks, MMAN not only enforces local and semantic consistency explicitly, but also avoids the poor convergence problem of adversarial networks when handling high resolution images. In our experiment, we validate that the two discriminators are complementary to each other in improving the human parsing accuracy. The proposed framework is capable of producing competitive parsing performance compared with the state-of-the-art methods, i.e., mIoU=46.81% and 59.91% on LIP and PASCAL-Person-Part, respectively. On a relatively small dataset PPSS, our pre-trained model demonstrates impressive generalization ability. The code is publicly available at https://github.com/RoyalVane/MMAN.

cs.CV↗

arXiv2018

Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors

In this paper, we present supervision-by-registration, an unsupervised approach to improve the precision of facial landmark detectors on both images and video. Our key observation is that the detections of the same landmark in adjacent frames should be coherent with registration, i.e., optical flow. Interestingly, the coherency of optical flow is a source of supervision that does not require manual labeling, and can be leveraged during detector training. For example, we can enforce in the training loss function that a detected landmark at frame$_{t-1}$ followed by optical flow tracking from frame$_{t-1}$ to frame$_t$ should coincide with the location of the detection at frame$_t$. Essentially, supervision-by-registration augments the training loss function with a registration loss, thus training the detector to have output that is not only close to the annotations in labeled images, but also consistent with registration on large amounts of unlabeled videos. End-to-end training with the registration loss is made possible by a differentiable Lucas-Kanade operation, which computes optical flow registration in the forward pass, and back-propagates gradients that encourage temporal coherency in the detector. The output of our method is a more precise image-based facial landmark detector, which can be applied to single images or video. With supervision-by-registration, we demonstrate (1) improvements in facial landmark detection on both images (300W, ALFW) and video (300VW, Youtube-Celebrities), and (2) significant reduction of jittering in video detections.

cs.CV↗

arXiv2018

Subaru/HiCIAO $HK_{\rm s}$ imaging of LkH$α$ 330 - multi-band detection of the gap and spiral-like structures

We present $H$- and $K_{\rm s}$-bands observations of the LkH$α$ 330 disk with a multi-band detection of the large gap and spiral-like structures. The morphology of the outer disk ($r\sim$$0\farcs3$) at PA=0--45$^\circ$ and PA=180--290$^\circ$ are likely density wave-induced spirals and comparison between our observational results and simulations suggests a planet formation. We have also investigated the azimuthal profiles at the ring and the outer-disk regions as well as radial profiles in the directions of the spiral-like structures and semi-major axis. Azimuthal analysis shows a large variety in wavelength and implies that the disk has non-axisymmetric dust distributions. The radial profiles in the major-axis direction (PA=$271^\circ$) suggest that the outer region ($r\geq0\farcs25$) may be influenced by shadows of the inner region of the disk. The spiral-like directions (PA=10$^\circ$ and 230$^\circ$) show different radial profiles, which suggests that the surfaces of the spiral-like structures are highly flared and/or have different dust properties. Finally, a color-map of the disk shows a lack of an outer eastern region in the $H$-band disk, which may hint the presence of an inner object that casts a directional shadow onto the disk.

astro-ph.EP↗

arXiv2018

Holographic Entanglement Entropy in Boundary Quantum Field Theory

We study the holographic entanglement entropy in a (d+1)-dimensional boundary quantum field theory at both the zero and finite temperature. The phase diagrams for the holographic entanglement entropy at various temperatures are obtained by solving the entangled surfaces in the different homology. We also verify the Araki-Lieb inequality and illustrate the entanglement plateau.

hep-th↗

arXiv2018

Subdivisions of the posteromedial cortex in disorders of consciousness

Evidence suggests that disruptions of the posteromedial cortex (PMC) and posteromedial corticothalamic connectivity contribute to disorders of consciousness (DOCs). While most previous studies treated the PMC as a whole, this structure is functionally heterogeneous. The present study investigated whether particular subdivisions of the PMC are specifically associated with DOCs. Participants were DOC patients, 21 vegetative state/unresponsive wakefulness syndrome (VS/UWS), 12 minimally conscious state (MCS), and 29 healthy controls. Individual PMC and thalamus were divided into distinct subdivisions by their fiber tractograpy to each other and default mode regions, and white matter integrity and brain activity between/within subdivisions were assessed. The thalamus was represented mainly in the dorsal and posterior portions of the PMC, and the white matter tracts connecting these subdivisions to the thalamus had less integrity in VS/UWS patients than in MCS patients and healthy controls, as well as in patients who did not recover after 12 months than in patients who did. The structural substrates were validated by finding impaired functional fluctuations within this PMC subdivision. This study is the first to show that tracts from dorsal and posterior subdivisions of the PMC to the thalamus contribute to DOCs.

q-bio.NC↗

arXiv2018

Deploy Large-Scale Deep Neural Networks in Resource Constrained IoT Devices with Local Quantization Region

Implementing large-scale deep neural networks with high computational complexity on low-cost IoT devices may inevitably be constrained by limited computation resource, making the devices hard to respond in real-time. This disjunction makes the state-of-art deep learning algorithms, i.e. CNN (Convolutional Neural Networks), incompatible with IoT world. We present a low-bit (range from 8-bit to 1-bit) scheme with our local quantization region algorithm. We use models in Caffe model zoo as our example tasks to evaluate the effect of our low precision data representation scheme. With the available of local quantization region, we find implementations on top of those schemes could greatly retain the model accuracy, besides the reduction of computational complexity. For example, our 8-bit scheme has no drops on top-1 and top-5 accuracy with 2x speedup on Intel Edison IoT platform. Implementations based on our 4-bit, 2-bit or 1-bit scheme are also applicable to IoT devices with advances of low computational complexity. For example, the drop on our task is only 0.7% when using 2-bit scheme, a scheme which could largely save transistors. Making low-bit scheme usable here opens a new door for further optimization on commodity IoT controller, i.e. extra speed-up could be achieved by replacing multiply-accumulate operations with the proposed table look-up operations. The whole study offers a new approach to relief the challenge of bring advanced deep learning algorithm to resource constrained low-cost IoT device.

cs.LG↗

arXiv2018

High-contrast Polarimetry Observation of T Tau Circumstellar Environment

We conducted high-contrast polarimetry observations of T Tau in the H-band, using the HiCIAO instrument mounted on the Subaru Telescope, revealing structures as near as 0.$\arcsec$1 from the stars T Tau N and T Tau S. The whole T Tau system is found to be surrounded by nebula-like envelopes, and several outflow-related structures are detected in these envelopes. We analyzed the detailed polarization patterns of the circumstellar structures near each component of this triple young star system and determined constraints on the circumstellar disks and outflow structures. We suggest that the nearly face-on circumstellar disk of T Tau N is no larger than 0.$\arcsec$8, or 117 AU, in the northwest, based on the existence of a hole in this direction, and no larger than 0.$\arcsec$27, or 40 AU, in the south. A new structure "N5" extends to about 0.$\arcsec$42, or 59 AU, on the southwest of the star, believed to be part of the disk. We suggest that T Tau S is surrounded by a highly inclined circumbinary disk with a radius of about 0.$\arcsec$3, or 44 AU, with a position angle of about 30$^\circ$, that is misaligned with the orbit of the T Tau S binary. After analyzing the positions and polarization vector patterns of the outflow-related structures, we suggest that T Tau S should trigger the well-known E-W outflow, and is also likely to be responsible for a southwest precessing outflow "coil" and a possible south outflow.

astro-ph.SR↗

arXiv2018

Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification

Person re-identification (re-ID) models trained on one domain often fail to generalize well to another. In our attempt, we present a "learning via translation" framework. In the baseline, we translate the labeled images from source to target domain in an unsupervised manner. We then train re-ID models with the translated images by supervised methods. Yet, being an essential part of this framework, unsupervised image-image translation suffers from the information loss of source-domain labels during translation. Our motivation is two-fold. First, for each image, the discriminative cues contained in its ID label should be maintained after translation. Second, given the fact that two domains have entirely different persons, a translated image should be dissimilar to any of the target IDs. To this end, we propose to preserve two types of unsupervised similarities, 1) self-similarity of an image before and after translation, and 2) domain-dissimilarity of a translated source image and a target image. Both constraints are implemented in the similarity preserving generative adversarial network (SPGAN) which consists of an Siamese network and a CycleGAN. Through domain adaptation experiment, we show that images generated by SPGAN are more suitable for domain adaptation and yield consistent and competitive re-ID accuracy on two large-scale datasets.

cs.CV↗