Search arXiv⌕ Search

arXiv subjects

Xiao Liu

Publications and source records attributed to Xiao Liu.

At least 415 records · Page 23Linked to original sources
arXiv2021

Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation

Unsupervised disentanglement learning is a crucial issue for understanding and exploiting deep generative models. Recently, SeFa tries to find latent disentangled directions by performing SVD on the first projection of a pre-trained GAN. However, it is only applied to the first layer and works in a post-processing way. Hessian Penalty minimizes the off-diagonal entries of the output's Hessian matrix to facilitate disentanglement, and can be applied to multi-layers.However, it constrains each entry of output independently, making it not sufficient in disentangling the latent directions (e.g., shape, size, rotation, etc.) of spatially correlated variations. In this paper, we propose a simple Orthogonal Jacobian Regularization (OroJaR) to encourage deep generative model to learn disentangled representations. It simply encourages the variation of output caused by perturbations on different latent dimensions to be orthogonal, and the Jacobian with respect to the input is calculated to represent this variation. We show that our OroJaR also encourages the output's Hessian matrix to be diagonal in an indirect manner. In contrast to the Hessian Penalty, our OroJaR constrains the output in a holistic way, making it very effective in disentangling latent dimensions corresponding to spatially correlated variations. Quantitative and qualitative experimental results show that our method is effective in disentangled and controllable image generation, and performs favorably against the state-of-the-art methods. Our code is available at https://github.com/csyxwei/OroJaR

cs.CV↗
arXiv2021

Pre-Trained Models: Past, Present and Future

Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success and become a milestone in the field of artificial intelligence (AI). Owing to sophisticated pre-training objectives and huge model parameters, large-scale PTMs can effectively capture knowledge from massive labeled and unlabeled data. By storing knowledge into huge parameters and fine-tuning on specific tasks, the rich knowledge implicitly encoded in huge parameters can benefit a variety of downstream tasks, which has been extensively demonstrated via experimental verification and empirical analysis. It is now the consensus of the AI community to adopt PTMs as backbone for downstream tasks rather than learning models from scratch. In this paper, we take a deep look into the history of pre-training, especially its special relation with transfer learning and self-supervised learning, to reveal the crucial position of PTMs in the AI development spectrum. Further, we comprehensively review the latest breakthroughs of PTMs. These breakthroughs are driven by the surge of computational power and the increasing availability of data, towards four important directions: designing effective architectures, utilizing rich contexts, improving computational efficiency, and conducting interpretation and theoretical analysis. Finally, we discuss a series of open problems and research directions of PTMs, and hope our view can inspire and advance the future study of PTMs.

cs.AI↗
arXiv2021

Systematic control of Raman scattering with topologically induced chirality of light

Stokes Raman scattering is known to be a particularly robust nonlinearity, occurring in virtually every material, with spectra defined by the material and strengths dependent on the material as well as light intensities. This ubiquity has made it an indispensable tool in spectroscopy, but also presents itself as a stubborn source of noise or parasitic emission in several applications. Here, we show that orbital angular momentum carrying light beams experiencing spin-orbit interactions can fundamentally alter the selection rules for Raman scattering. This enables tailoring its spectral shape (by over half the Raman shift in a given material) as well as strength (by about 100 times) simply by controlling the topological charge of light, which is a capability of utility across the multitude of applications where modulating Raman scattering is desired.

physics.optics↗
arXiv2021

UniCon: Unified Context Network for Robust Active Speaker Detection

We introduce a new efficient framework, the Unified Context Network (UniCon), for robust active speaker detection (ASD). Traditional methods for ASD usually operate on each candidate's pre-cropped face track separately and do not sufficiently consider the relationships among the candidates. This potentially limits performance, especially in challenging scenarios with low-resolution faces, multiple candidates, etc. Our solution is a novel, unified framework that focuses on jointly modeling multiple types of contextual information: spatial context to indicate the position and scale of each candidate's face, relational context to capture the visual relationships among the candidates and contrast audio-visual affinities with each other, and temporal context to aggregate long-term information and smooth out local uncertainties. Based on such information, our model optimizes all candidates in a unified process for robust and reliable ASD. A thorough ablation study is performed on several challenging ASD benchmarks under different settings. In particular, our method outperforms the state-of-the-art by a large margin of about 15% mean Average Precision (mAP) absolute on two challenging subsets: one with three candidate speakers, and the other with faces smaller than 64 pixels. Together, our UniCon achieves 92.0% mAP on the AVA-ActiveSpeaker validation set, surpassing 90% for the first time on this challenging dataset at the time of submission. Project website: https://unicon-asd.github.io/.

cs.CV↗
arXiv2021

Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval

The current state-of-the-art image-sentence retrieval methods implicitly align the visual-textual fragments, like regions in images and words in sentences, and adopt attention modules to highlight the relevance of cross-modal semantic correspondences. However, the retrieval performance remains unsatisfactory due to a lack of consistent representation in both semantics and structural spaces. In this work, we propose to address the above issue from two aspects: (i) constructing intrinsic structure (along with relations) among the fragments of respective modalities, e.g., "dog $\to$ play $\to$ ball" in semantic structure for an image, and (ii) seeking explicit inter-modal structural and semantic correspondence between the visual and textual modalities. In this paper, we propose a novel Structured Multi-modal Feature Embedding and Alignment (SMFEA) model for image-sentence retrieval. In order to jointly and explicitly learn the visual-textual embedding and the cross-modal alignment, SMFEA creates a novel multi-modal structured module with a shared context-aware referral tree. In particular, the relations of the visual and textual fragments are modeled by constructing Visual Context-aware Structured Tree encoder (VCS-Tree) and Textual Context-aware Structured Tree encoder (TCS-Tree) with shared labels, from which visual and textual features can be jointly learned and optimized. We utilize the multi-modal tree structure to explicitly align the heterogeneous image-sentence data by maximizing the semantic and structural similarity between corresponding inter-modal tree nodes. Extensive experiments on Microsoft COCO and Flickr30K benchmarks demonstrate the superiority of the proposed model in comparison to the state-of-the-art methods.

cs.CV↗
arXiv2021

Robotic Communications for 5G and Beyond: Challenges and Research Opportunities

The ongoing surge in applications of robotics brings both opportunities and challenges for the fifth-generation (5G) and beyond (B5G) of communication networks. This article focuses on 5G/B5G-enabled terrestrial robotic communications with an emphasis on distinct characteristics of such communications. Firstly, signal and spatial modeling for robotic communications are presented. To elaborate further, both the benefits and challenges derived from robots' mobility are discussed. As a further advance, a novel simultaneous localization and radio mapping (SLARM) framework is proposed for integrating localization and communications into robotic networks. Furthermore, dynamic trajectory design and resource allocation for both indoor and outdoor robots are provided to verify the performance of robotic communications in the context of typical robotic application scenarios.

cs.RO↗
arXiv2021

Locality-aware Channel-wise Dropout for Occluded Face Recognition

Face recognition remains a challenging task in unconstrained scenarios, especially when faces are partially occluded. To improve the robustness against occlusion, augmenting the training images with artificial occlusions has been proved as a useful approach. However, these artificial occlusions are commonly generated by adding a black rectangle or several object templates including sunglasses, scarfs and phones, which cannot well simulate the realistic occlusions. In this paper, based on the argument that the occlusion essentially damages a group of neurons, we propose a novel and elegant occlusion-simulation method via dropping the activations of a group of neurons in some elaborately selected channel. Specifically, we first employ a spatial regularization to encourage each feature channel to respond to local and different face regions. In this way, the activations affected by an occlusion in a local region are more likely to be located in a single feature channel. Then, the locality-aware channel-wise dropout (LCD) is designed to simulate the occlusion by dropping out the entire feature channel. Furthermore, by randomly dropping out several feature channels, our method can well simulate the occlusion of larger area. The proposed LCD can encourage its succeeding layers to minimize the intra-class feature variance caused by occlusions, thus leading to improved robustness against occlusion. In addition, we design an auxiliary spatial attention module by learning a channel-wise attention vector to reweight the feature channels, which improves the contributions of non-occluded regions. Extensive experiments on various benchmarks show that the proposed method outperforms state-of-the-art methods with a remarkable improvement.

cs.CV↗
arXiv2021

3rd Place Solution for Short-video Face Parsing Challenge

This is a short technical report introducing the solution of Team Rat for Short-video Parsing Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021. In this report, we propose an Edge-Aware Network (EANet) that uses edge information to refine the segmentation edge. To further obtain the finer edge results, we introduce edge attention loss that only compute cross entropy on the edges, it can effectively reduce the classification error around edge and get more smooth boundary. Benefiting from the edge information and edge attention loss, the proposed EANet achieves 86.16\% accuracy in the Short-video Face Parsing track of the 3rd Person in Context (PIC) Workshop and Challenge, ranked the third place.

cs.CV↗
arXiv2021

Unsupervised Neural Rendering for Image Hazing

Image hazing aims to render a hazy image from a given clean one, which could be applied to a variety of practical applications such as gaming, filming, photographic filtering, and image dehazing. To generate plausible haze, we study two less-touched but challenging problems in hazy image rendering, namely, i) how to estimate the transmission map from a single image without auxiliary information, and ii) how to adaptively learn the airlight from exemplars, i.e., unpaired real hazy images. To this end, we propose a neural rendering method for image hazing, dubbed as HazeGEN. To be specific, HazeGEN is a knowledge-driven neural network which estimates the transmission map by leveraging a new prior, i.e., there exists the structure similarity (e.g., contour and luminance) between the transmission map and the input clean image. To adaptively learn the airlight, we build a neural module based on another new prior, i.e., the rendered hazy image and the exemplar are similar in the airlight distribution. To the best of our knowledge, this could be the first attempt to deeply rendering hazy images in an unsupervised fashion. Comparing with existing haze generation methods, HazeGEN renders the hazy images in an unsupervised, learnable, and controllable manner, thus avoiding the labor-intensive efforts in paired data collection and the domain-shift issue in haze generation. Extensive experiments show the promising performance of our method comparing with some baselines in both qualitative and quantitative comparisons. The code will be released on GitHub after acceptance.

cs.CV↗
arXiv2021

Using Noisy Self-Reports to Predict Twitter User Demographics

Computational social science studies often contextualize content analysis within standard demographics. Since demographics are unavailable on many social media platforms (e.g. Twitter) numerous studies have inferred demographics automatically. Despite many studies presenting proof of concept inference of race and ethnicity, training of practical systems remains elusive since there are few annotated datasets. Existing datasets are small, inaccurate, or fail to cover the four most common racial and ethnic groups in the United States. We present a method to identify self-reports of race and ethnicity from Twitter profile descriptions. Despite errors inherent in automated supervision, we produce models with good performance when measured on gold standard self-report survey data. The result is a reproducible method for creating large-scale training resources for race and ethnicity.

cs.CL↗
arXiv2021

Gaze Estimation with an Ensemble of Four Architectures

This paper presents a method for gaze estimation according to face images. We train several gaze estimators adopting four different network architectures, including an architecture designed for gaze estimation (i.e.,iTracker-MHSA) and three originally designed for general computer vision tasks(i.e., BoTNet, HRNet, ResNeSt). Then, we select the best six estimators and ensemble their predictions through a linear combination. The method ranks the first on the leader-board of ETH-XGaze Competition, achieving an average angular error of $3.11^{\circ}$ on the ETH-XGaze test set.

cs.CV↗
arXiv2021

Controllable cardiac synthesis via disentangled anatomy arithmetic

Acquiring annotated data at scale with rare diseases or conditions remains a challenge. It would be extremely useful to have a method that controllably synthesizes images that can correct such underrepresentation. Assuming a proper latent representation, the idea of a "latent vector arithmetic" could offer the means of achieving such synthesis. A proper representation must encode the fidelity of the input data, preserve invariance and equivariance, and permit arithmetic operations. Motivated by the ability to disentangle images into spatial anatomy (tensor) factors and accompanying imaging (vector) representations, we propose a framework termed "disentangled anatomy arithmetic", in which a generative model learns to combine anatomical factors of different input images such that when they are re-entangled with the desired imaging modality (e.g. MRI), plausible new cardiac images are created with the target characteristics. To encourage a realistic combination of anatomy factors after the arithmetic step, we propose a localized noise injection network that precedes the generator. Our model is used to generate realistic images, pathology labels, and segmentation masks that are used to augment the existing datasets and subsequently improve post-hoc classification and segmentation tasks. Code is publicly available at https://github.com/vios-s/DAA-GAN.

eess.IV↗
arXiv2021

Boost-R: Gradient Boosted Trees for Recurrence Data

Recurrence data arise from multi-disciplinary domains spanning reliability, cyber security, healthcare, online retailing, etc. This paper investigates an additive-tree-based approach, known as Boost-R (Boosting for Recurrence Data), for recurrent event data with both static and dynamic features. Boost-R constructs an ensemble of gradient boosted additive trees to estimate the cumulative intensity function of the recurrent event process, where a new tree is added to the ensemble by minimizing the regularized L2 distance between the observed and predicted cumulative intensity. Unlike conventional regression trees, a time-dependent function is constructed by Boost-R on each tree leaf. The sum of these functions, from multiple trees, yields the ensemble estimator of the cumulative intensity. The divide-and-conquer nature of tree-based methods is appealing when hidden sub-populations exist within a heterogeneous population. The non-parametric nature of regression trees helps to avoid parametric assumptions on the complex interactions between event processes and features. Critical insights and advantages of Boost-R are investigated through comprehensive numerical examples. Datasets and computer code of Boost-R are made available on GitHub. To our best knowledge, Boost-R is the first gradient boosted additive-tree-based approach for modeling large-scale recurrent event data with both static and dynamic feature information.

cs.LG↗
arXiv2021

1st Place Solutions for UG2+ Challenge 2021 -- (Semi-)supervised Face detection in the low light condition

In this technical report, we briefly introduce the solution of our team "TAL-ai" for (Semi-) supervised Face detection in the low light condition in UG2+ Challenge in CVPR 2021. By conducting several experiments with popular image enhancement methods and image transfer methods, we pulled the low light image and the normal image to a more closer domain. And it is observed that using these data to training can achieve better performance. We also adapt several popular object detection frameworks, e.g., DetectoRS, Cascade-RCNN, and large backbone like Swin-transformer. Finally, we ensemble several models which achieved mAP 74.89 on the testing set, ranking 1st on the final leaderboard.

cs.CV↗
arXiv2021

Multi-Granularity Network with Modal Attention for Dense Affective Understanding

Video affective understanding, which aims to predict the evoked expressions by the video content, is desired for video creation and recommendation. In the recent EEV challenge, a dense affective understanding task is proposed and requires frame-level affective prediction. In this paper, we propose a multi-granularity network with modal attention (MGN-MA), which employs multi-granularity features for better description of the target frame. Specifically, the multi-granularity features could be divided into frame-level, clips-level and video-level features, which corresponds to visual-salient content, semantic-context and video theme information. Then the modal attention fusion module is designed to fuse the multi-granularity features and emphasize more affection-relevant modals. Finally, the fused feature is fed into a Mixtures Of Experts (MOE) classifier to predict the expressions. Further employing model-ensemble post-processing, the proposed method achieves the correlation score of 0.02292 in the EEV challenge.

cs.CV↗
arXiv2021

Heralded entanglement distribution between two absorptive quantum memories

Owing to the inevitable loss in communication channels, the distance of entanglement distribution is limited to approximately 100 kilometres on the ground. Quantum repeaters can circumvent this problem by using quantum memory and entanglement swapping. As the elementary link of a quantum repeater, the heralded distribution of two-party entanglement between two remote nodes has only been realized with built-in-type quantum memories. These schemes suffer from the trade-off between multiplexing capacity and deterministic properties and hence hinder the development of efficient quantum repeaters. Quantum repeaters based on absorptive quantum memories can overcome such limitations because they separate the quantum memories and the quantum light sources. Here we present an experimental demonstration of heralded entanglement between absorptive quantum memories. We build two nodes separated by 3.5 metres, each containing a polarization-entangled photon-pair source and a solid-state quantum memory with bandwidth up to 1 gigahertz. A joint Bell-state measurement in the middle station heralds the successful distribution of maximally entangled states between the two quantum memories with a fidelity of 80.4 $\pm$ 2.2 per cent ($\pm$1 standard deviation). The quantum nodes and channels demonstrated here can serve as an elementary link of a quantum repeater. Moreover, the wideband absorptive quantum memories used in the nodes are compatible with deterministic entanglement sources and can simultaneously support multiplexing, which paves the way for the construction of practical solid-state quantum repeaters and high-speed quantum networks.

quant-ph↗