arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 955 records · Page 53Linked to original sources

arXiv2019

Multi-scale discriminative Region Discovery for Weakly-Supervised Object Localization

Localizing objects with weak supervision in an image is a key problem of the research in computer vision community. Many existing Weakly-Supervised Object Localization (WSOL) approaches tackle this problem by estimating the most discriminative regions with feature maps (activation maps) obtained by Deep Convolutional Neural Network, that is, only the objects or parts of them with the most discriminative response will be located. However, the activation maps often display different local maximum responses or relatively weak response when one image contains multiple objects with the same type or small objects. In this paper, we propose a simple yet effective multi-scale discriminative region discovery method to localize not only more integral objects but also as many as possible with only image-level class labels. The gradient weights flowing into different convolutional layers of CNN are taken as the input of our method, which is different from previous methods only considering that of the final convolutional layer. To mine more discriminative regions for the task of object localization, the multiple local maximum from the gradient weight maps are leveraged to generate the localization map with a parallel sliding window. Furthermore, multi-scale localization maps from different convolutional layers are fused to produce the final result. We evaluate the proposed method with the foundation of VGGnet on the ILSVRC 2016, CUB-200-2011 and PASCAL VOC 2012 datasets. On ILSVRC 2016, the proposed method yields the Top-1 localization error of 48.65\%, which outperforms previous results by 2.75\%. On PASCAL VOC 2012, our approach achieve the highest localization accuracy of 0.43. Even for CUB-200-2011 dataset, our method still achieves competitive results.

cs.CV↗

arXiv2019

FASTER Recurrent Networks for Efficient Video Classification

Typical video classification methods often divide a video into short clips, do inference on each clip independently, then aggregate the clip-level predictions to generate the video-level results. However, processing visually similar clips independently ignores the temporal structure of the video sequence, and increases the computational cost at inference time. In this paper, we propose a novel framework named FASTER, i.e., Feature Aggregation for Spatio-TEmporal Redundancy. FASTER aims to leverage the redundancy between neighboring clips and reduce the computational cost by learning to aggregate the predictions from models of different complexities. The FASTER framework can integrate high quality representations from expensive models to capture subtle motion information and lightweight representations from cheap models to cover scene changes in the video. A new recurrent network (i.e., FAST-GRU) is designed to aggregate the mixture of different representations. Compared with existing approaches, FASTER can reduce the FLOPs by over 10x? while maintaining the state-of-the-art accuracy across popular datasets, such as Kinetics, UCF-101 and HMDB-51.

cs.CV↗

arXiv2019

Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification

Prevailing deep convolutional neural networks (CNNs) for person re-IDentification (reID) are usually built upon ResNet or VGG backbones, which were originally designed for classification. Because reID is different from classification, the architecture should be modified accordingly. We propose to automatically search for a CNN architecture that is specifically suitable for the reID task. There are three aspects to be tackled. First, body structural information plays an important role in reID but it is not encoded in backbones. Second, Neural Architecture Search (NAS) automates the process of architecture design without human effort, but no existing NAS methods incorporate the structure information of input images. Third, reID is essentially a retrieval task but current NAS algorithms are merely designed for classification. To solve these problems, we propose a retrieval-based search algorithm over a specifically designed reID search space, named Auto-ReID. Our Auto-ReID enables the automated approach to find an efficient and effective CNN architecture for reID. Extensive experiments demonstrate that the searched architecture achieves state-of-the-art performance while reducing 50% parameters and 53% FLOPs compared to others.

cs.CV↗

arXiv2019

Linear spectropolarimetry of 35 Type Ia Supernovae with VLT/FORS: An analysis of the Si II line polarization

Spectropolarimetry enables us to measure the geometry and chemical structure of the ejecta in supernova explosions, which is fundamental for the understanding of their explosion mechanism(s) and progenitor systems. We collected archival data of 35 Type Ia Supernovae (SNe Ia), observed with FORS on the Very Large Telescope at 127 epochs in total. We examined the polarization of the Si II $λ$6355 $Å$ line (p$_{\rm Si II}$) as a function of time which is seen to peak at a range of various polarization degrees and epochs relative to maximum brightness. We reproduced the $Δ$m$_{15}$-p$_{\rm Si II}$ relationship identified in a previous study, and show that subluminous and transitional objects display polarization values below the $Δ$m$_{15}$-p$_{\rm Si II}$ relationship for normal SNe Ia. We found a statistically significant linear relationship between the polarization of the Si II $λ$6355 $Å$ line before maximum brightness and the Si II line velocity and suggest that this, along with the $Δ$m$_{15}$-p$_{\rm Si II}$ relationship, may be explained in the context of a delayed-detonation model. In contrast, we compared our observations to numerical predictions in the $Δ$m$_{15}$-v$_{\rm Si II}$ plane and found a dichotomy in the polarization properties between Chandrasekhar and sub-Chandrasekhar mass explosions, which supports the possibility of two distinct explosion mechanisms. A subsample of SNe display evolution of loops in the $q$-$u$ plane that suggests a more complex Si structure with depth. This insight, which could not be gleaned from total flux spectra, presents a new constraint on explosion models. Finally, we compared our statistical sample of the Si II polarization to quantitative predictions of the polarization levels for the double-detonation, delayed-detonation, and violent-merger models.

astro-ph.HE↗

arXiv2019

Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection

Facial landmark detection aims to localize the anatomically defined points of human faces. In this paper, we study facial landmark detection from partially labeled facial images. A typical approach is to (1) train a detector on the labeled images; (2) generate new training samples using this detector's prediction as pseudo labels of unlabeled images; (3) retrain the detector on the labeled samples and partial pseudo labeled samples. In this way, the detector can learn from both labeled and unlabeled data to become robust. In this paper, we propose an interaction mechanism between a teacher and two students to generate more reliable pseudo labels for unlabeled data, which are beneficial to semi-supervised facial landmark detection. Specifically, the two students are instantiated as dual detectors. The teacher learns to judge the quality of the pseudo labels generated by the students and filter out unqualified samples before the retraining stage. In this way, the student detectors get feedback from their teacher and are retrained by premium data generated by itself. Since the two students are trained by different samples, a combination of their predictions will be more robust as the final prediction compared to either prediction. Extensive experiments on 300-W and AFLW benchmarks show that the interactions between teacher and students contribute to better utilization of the unlabeled data and achieves state-of-the-art performance.

cs.CV↗

arXiv2019

Recognizing Part Attributes with Insufficient Data

Recognizing attributes of objects and their parts is important to many computer vision applications. Although great progress has been made to apply object-level recognition, recognizing the attributes of parts remains less applicable since the training data for part attributes recognition is usually scarce especially for internet-scale applications. Furthermore, most existing part attribute recognition methods rely on the part annotation which is more expensive to obtain. To solve the data insufficiency problem and get rid of dependence on the part annotation, we introduce a novel Concept Sharing Network (CSN) for part attribute recognition. A great advantage of CSN is its capability of recognizing the part attribute (a combination of part location and appearance pattern) that has insufficient or zero training data, by learning the part location and appearance pattern respectively from the training data that usually mix them in a single label. Extensive experiments on CUB-200-2011 [51], CelebA [35] and a newly proposed human attribute dataset demonstrate the effectiveness of CSN and its advantages over other methods, especially for the attributes with few training samples. Further experiments show that CSN can also perform zero-shot part attribute recognition. The code will be made available at https://github.com/Zhaoxiangyun/Concept-Sharing-Network.

cs.CV↗

arXiv2019

Overview on High energy String Scattering Amplitudes and Symmetries of String Theory

We overview symmetries of string scattering amplitudes in the high energy limits of both the fixed angle or Gross regime (GR) and the fixed momentum transfer or Regge regime (RR). We calculated high energy string scattering amplitudes (SSA) at arbitrary mass levels for both regimes. We discovered the infinite linear relations among fixed angle string amplitudes and the infinite recurrence relations among Regge string amplitudes. The linear relations we obtained in the GR corrected the saddle point calculations by Gross, Gross and Mende. In addition, for the high energy closed string scatterings, our results differ from theirs by an oscillating prefactor which was crucial to recover the KLT relation valid for all energies. We showed that all the high energy string amplitudes can be solved by the linear or recurrence relations so that all the string amplitudes can be expressed in terms of a single string amplitude. We further found that, at each mass level, the ratios among the fixed angle amplitudes can be extracted from the Regge string scattering amplitudes. Finally, we review the recent developments on the discovery of infinite number of recurrence relations valid for all energies among Lauricella SSA. The symmetries or relations among SSA at various limits obtained previously can be exactly reproduced. It leads us to argue that the known SL(K+3,C) dynamical symmetry of the Lauricella function maybe crucial to probe spacetime symmetry of string theory.

hep-th↗

arXiv2019

Attract or Distract: Exploit the Margin of Open Set

Open set domain adaptation aims to diminish the domain shift across domains, with partially shared classes. There exist unknown target samples out of the knowledge of source domain. Compared to the close set setting, how to separate the unknown (unshared) class from the known (shared) ones plays a key role. Whereas, previous methods did not emphasize the semantic structure of the open set data, which may introduce bias into the domain alignment and confuse the classifier around the decision boundary. In this paper, we exploit the semantic structure of open set data from two aspects: 1) Semantic Categorical Alignment, which aims to achieve good separability of target known classes by categorically aligning the centroid of target with the source. 2)Semantic Contrastive Mapping, which aims to push the unknown class away from the decision boundary. Empirically, we demonstrate that our method performs favourably against the state-of-the-art methods on representative benchmarks, e.g. Digit datasets and Office-31 datasets.

cs.CV↗

arXiv2019

An Algorithm for Graph-Fused Lasso Based on Graph Decomposition

This work proposes a new algorithm for solving the graph-fused lasso (GFL), a method for parameter estimation that operates under the assumption that the signal tends to be locally constant over a predefined graph structure. The proposed method applies the alternating direction method of multipliers (ADMM) algorithm and is based on the decomposition of the objective function into two components. While ADMM has been widely used in this problem, existing works such as network lasso decompose the objective function into the loss function component and the total variation penalty component. In comparison, this work proposes to decompose the objective function into two components, where one component is the loss function plus part of the total variation penalty, and the other component is the remaining total variation penalty. Compared with the network lasso algorithm, this method has a smaller computational cost per iteration and converges faster in most simulations numerically.

math.OC↗

arXiv2019

Cascaded Revision Network for Novel Object Captioning

Image captioning, a challenging task where the machine automatically describes an image by sentences, has drawn significant attention in recent years. Despite the remarkable improvements of recent approaches, however, these methods are built upon a large set of training image-sentence pairs. The expensive labor efforts hence limit the captioning model to describe the wider world. In this paper, we present a novel network structure, Cascaded Revision Network, which aims at relieving the problem by equipping the model with out-of-domain knowledge. CRN first tries its best to describe an image using the existing vocabulary from in-domain knowledge. Due to the lack of out-of-domain knowledge, the caption may be inaccurate or include ambiguous words for the image with unknown (novel) objects. We propose to re-edit the primary captioning sentence by a series of cascaded operations. We introduce a perplexity predictor to find out which words are most likely to be inaccurate given the input image. Thereafter, we utilize external knowledge from a pre-trained object detection model and select more accurate words from detection results by the visual matching module. In the last step, we design a semantic matching module to ensure that the novel object is fit in the right position. By this novel cascaded captioning-revising mechanism, CRN can accurately describe images with unseen objects. We validate the proposed method with state-of-the-art performance on the held-out MSCOCO dataset as well as scale to ImageNet, demonstrating the effectiveness of this method.

cs.MM↗

arXiv2019

Learning to Adapt Invariance in Memory for Person Re-identification

This work considers the problem of unsupervised domain adaptation in person re-identification (re-ID), which aims to transfer knowledge from the source domain to the target domain. Existing methods are primary to reduce the inter-domain shift between the domains, which however usually overlook the relations among target samples. This paper investigates into the intra-domain variations of the target domain and proposes a novel adaptation framework w.r.t. three types of underlying invariance, i.e., Exemplar-Invariance, Camera-Invariance, and Neighborhood-Invariance. Specifically, an exemplar memory is introduced to store features of samples, which can effectively and efficiently enforce the invariance constraints over the global dataset. We further present the Graph-based Positive Prediction (GPP) method to explore reliable neighbors for the target domain, which is built upon the memory and is trained on the source samples. Experiments demonstrate that 1) the three invariance properties are indispensable for effective domain adaptation, 2) the memory plays a key role in implementing invariance learning and improves the performance with limited extra computation cost, 3) GPP could facilitate the invariance learning and thus significantly improves the results, and 4) our approach produces new state-of-the-art adaptation accuracy on three re-ID large-scale benchmarks.

cs.CV↗

arXiv2019

Inclusive diffractive heavy quarkonium photoproduction in pp, pA and AA collisions

The inclusive $J/Ψ$ production by direct and resolved photoproduction in the $γ$p scattering is calculated based on the nonrelativistic quantum chromodynamics (NRQCD) factorization formalism, which is in good agreement with the experimental data of total cross section distribution of heavy quarkonium production at HERA. Then we extend the formalism including the direct and resolved photoproduction processes to resolved pomeron model to study the heavy quarkonium photoproduction at the LHC energies. We present the predictions of rapidity and transverse momentum distributions of the inclusive diffractive $J/Ψ$, $Ψ(2S)$ and $Υ$ photoproduction in pp, pPb and PbPb collisions at the LHC energies. Our numerical results indicate that the resolved photoproduction processes play an important role in the heavy quarkonium production. Especially for pp collisions, the contribution of resolved photoproduction processes is the largest, which can reach to $28\%$, $13\%$ and $44\%$ for the rapidity distributions of $J/Ψ$, $Ψ(2S)$ and $Υ$ inclusive diffractive photoproduction, respectively.

hep-ph↗

arXiv2019

Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration

Previous works utilized ''smaller-norm-less-important'' criterion to prune filters with smaller norm values in a convolutional neural network. In this paper, we analyze this norm-based criterion and point out that its effectiveness depends on two requirements that are not always met: (1) the norm deviation of the filters should be large; (2) the minimum norm of the filters should be small. To solve this problem, we propose a novel filter pruning method, namely Filter Pruning via Geometric Median (FPGM), to compress the model regardless of those two requirements. Unlike previous methods, FPGM compresses CNN models by pruning filters with redundancy, rather than those with ''relatively less'' importance. When applied to two image classification benchmarks, our method validates its usefulness and strengths. Notably, on CIFAR-10, FPGM reduces more than 52% FLOPs on ResNet-110 with even 2.69% relative accuracy improvement. Moreover, on ILSVRC-2012, FPGM reduces more than 42% FLOPs on ResNet-101 without top-5 accuracy drop, which has advanced the state-of-the-art. Code is publicly available on GitHub: https://github.com/he-y/filter-pruning-geometric-median

cs.CV↗

arXiv2019

Baidu-UTS Submission to the EPIC-Kitchens Action Recognition Challenge 2019

In this report, we present the Baidu-UTS submission to the EPIC-Kitchens Action Recognition Challenge in CVPR 2019. This is the winning solution to this challenge. In this task, the goal is to predict verbs, nouns, and actions from the vocabulary for each video segment. The EPIC-Kitchens dataset contains various small objects, intense motion blur, and occlusions. It is challenging to locate and recognize the object that an actor interacts with. To address these problems, we utilize object detection features to guide the training of 3D Convolutional Neural Networks (CNN), which can significantly improve the accuracy of noun prediction. Specifically, we introduce a Gated Feature Aggregator module to learn from the clip feature and the object feature. This module can strengthen the interaction between the two kinds of activations and avoid gradient exploding. Experimental results demonstrate our approach outperforms other methods on both seen and unseen test set.

cs.CV↗

arXiv2019

Observations of Type Ia Supernova 2014J for Nearly 900 Days and Constraints on Its Progenitor System

We present extensive ground-based and $Hubble~Space~Telescope$ ($HST$) photometry of the highly reddened, very nearby type Ia supernova (SN Ia) 2014J in M82, covering the phases from 9 days before to about 900 days after the $B$-band maximum. SN 2014J is similar to other normal SNe Ia near the maximum light, but it shows flux excess in the $B$ band in the early nebular phase. This excess flux emission can be due to light scattering by some structures of circumstellar materials located at a few 10$^{17}$ cm, consistent with a single degenerate progenitor system or a double degenerate progenitor system with mass outflows in the final evolution or magnetically driven winds around the binary system. At t$\sim$+300 to $\sim$+500 days past the $B$-band maximum, the light curve of SN 2014J shows a faster decline relative to the $^{56}$Ni decay. Such a feature can be attributed to the significant weakening of the emission features around [Fe III] $λ$4700 and [Fe II] $λ$5200 rather than the positron escape as previously suggested. Analysis of the $HST$ images taken at t$>$600 days confirms that the luminosity of SN 2014J maintains a flat evolution at the very late phase. Fitting the late-time pseudo-bolometric light curve with radioactive decay of $^{56}$Ni, $^{57}$Ni and $^{55}$Fe isotopes, we obtain the mass ratio $^{57}$Ni/$^{56}$Ni as $0.035 \pm 0.011$, which is consistent with the corresponding value predicted from the 2D and 3D delayed-detonation models. Combined with early-time analysis, we propose that delayed-detonation through single degenerate scenario is most likely favored for SN 2014J.

astro-ph.SR↗

arXiv2019

The Cold and Dusty Circumstellar Matter around Fast-expanding Type Ia Supernovae

Type Ia supernovae (SNe Ia) play key roles in revealing the accelerating expansion of the universe, but our knowledge about their progenitors is still very limited. Here we report the discovery of a rigid dichotomy in circumstellar (CS) environments around two subclasses of type Ia supernovae (SNe Ia) as defined by their distinct photospheric velocities. For the SNe Ia with high photospheric velocities (HV), we found a significant excess flux in blue light during 60-100 days past maximum, while this phenomenon is absent for SNe with normal photospheric velocity (Normal). This blue excess can be attributed to light echoes by circumstellar dust located at a distance of about 1-3x10^{17} cm from the HV subclass. Moreover, we also found that the HV SNe Ia show systematically evolving Na I absorption line by performing a systematic search of variable Na I absorption lines in spectra of all SNe Ia, whereas this evolution is rarely seen in Normal ones. The evolving Na I absorption can be modeled in terms of photoionization model, with the location of the gas clouds at a distance of about 2x10^{17} cm, in striking agreement with the location of CS dust inferred from B-band light curve excess. These observations show clearly that the progenitors of HV and Normal subclasses are systematically different, suggesting that they are likely from single and double degenerate progenitor systems, respectively.

astro-ph.HE↗

arXiv2019

Improving Person Re-identification by Attribute and Identity Learning

Person re-identification (re-ID) and attribute recognition share a common target at learning pedestrian descriptions. Their difference consists in the granularity. Most existing re-ID methods only take identity labels of pedestrians into consideration. However, we find the attributes, containing detailed local descriptions, are beneficial in allowing the re-ID model to learn more discriminative feature representations. In this paper, based on the complementarity of attribute labels and ID labels, we propose an attribute-person recognition (APR) network, a multi-task network which learns a re-ID embedding and at the same time predicts pedestrian attributes. We manually annotate attribute labels for two large-scale re-ID datasets, and systematically investigate how person re-ID and attribute recognition benefit from each other. In addition, we re-weight the attribute predictions considering the dependencies and correlations among the attributes. The experimental results on two large-scale re-ID benchmarks demonstrate that by learning a more discriminative representation, APR achieves competitive re-ID performance compared with the state-of-the-art methods. We use APR to speed up the retrieval process by ten times with a minor accuracy drop of 2.92% on Market-1501. Besides, we also apply APR on the attribute recognition task and demonstrate improvement over the baselines.

cs.CV↗

arXiv2019

Synthesis and Observation of Non-Abelian Gauge Fields in Real Space

Gauge fields, real or synthetic, are crucial for understanding and manipulation of physical systems. The associated geometric phases can be measured, for example, from the Aharonov--Bohm interference. So far, real-space realizations of gauge fields have been limited to Abelian (commutative) ones. Here we report an experimental synthesis of non-Abelian gauge fields in real space and the observation of the non-Abelian Aharonov--Bohm effect with classical waves and classical fluxes. Based on optical mode degeneracy, we break time-reversal symmetry in different manners---via temporal modulation and the Faraday effect---to synthesize tunable non-Abelian gauge fields. The Sagnac interference of two final states, obtained by reversely-ordered path integrals, demonstrates the non-commutativity of the gauge fields. Our work introduces real-space building blocks for non-Abelian gauge fields, relevant for classical and quantum exotic topological phenomena.

physics.optics↗