arXiv subjects

Liming Chen

Publications and source records attributed to Liming Chen.

At least 109 records · Page 6Linked to original sources

arXiv2021

A 3D GAN for Improved Large-pose Facial Recognition

Facial recognition using deep convolutional neural networks relies on the availability of large datasets of face images. Many examples of identities are needed, and for each identity, a large variety of images are needed in order for the network to learn robustness to intra-class variation. In practice, such datasets are difficult to obtain, particularly those containing adequate variation of pose. Generative Adversarial Networks (GANs) provide a potential solution to this problem due to their ability to generate realistic, synthetic images. However, recent studies have shown that current methods of disentangling pose from identity are inadequate. In this work we incorporate a 3D morphable model into the generator of a GAN in order to learn a nonlinear texture model from in-the-wild images. This allows generation of new, synthetic identities, and manipulation of pose, illumination and expression without compromising the identity. Our synthesised data is used to augment training of facial recognition networks with performance evaluated on the challenging CFP and CPLFW datasets.

cs.CV↗

arXiv2021

Connecting Images through Time and Sources: Introducing Low-data, Heterogeneous Instance Retrieval

With impressive results in applications relying on feature learning, deep learning has also blurred the line between algorithm and data. Pick a training dataset, pick a backbone network for feature extraction, and voilà ; this usually works for a variety of use cases. But the underlying hypothesis that there exists a training dataset matching the use case is not always met. Moreover, the demand for interconnections regardless of the variations of the content calls for increasing generalization and robustness in features. An interesting application characterized by these problematics is the connection of historical and cultural databases of images. Through the seemingly simple task of instance retrieval, we propose to show that it is not trivial to pick features responding well to a panel of variations and semantic content. Introducing a new enhanced version of the Alegoria benchmark, we compare descriptors using the detailed annotations. We further give insights about the core problems in instance retrieval, testing four state-of-the-art additional techniques to increase performance.

cs.CV↗

arXiv2021

A Survey of Hybrid Human-Artificial Intelligence for Social Computing

Along with the development of modern computing technology and social sciences, both theoretical research and practical applications of social computing have been continuously extended. In particular with the boom of artificial intelligence (AI), social computing is significantly influenced by AI. However, the conventional technologies of AI have drawbacks in dealing with more complicated and dynamic problems. Such deficiency can be rectified by hybrid human-artificial intelligence (H-AI) which integrates both human intelligence and AI into one unity, forming a new enhanced intelligence. H-AI in dealing with social problems shows the advantages that AI can not surpass. This paper firstly introduces the concept of H-AI. AI is the intelligence in the transition stage of H-AI, so the latest research progresses of AI in social computing are reviewed. Secondly, it summarizes typical challenges faced by AI in social computing, and makes it possible to introduce H-AI to solve these challenges. Finally, the paper proposes a holistic framework of social computing combining with H-AI, which consists of four layers: object layer, base layer, analysis layer, and application layer. It represents H-AI has significant advantages over AI in solving social problems.

cs.AI↗

arXiv2021

Discriminative Noise Robust Sparse Orthogonal Label Regression-based Domain Adaptation

Domain adaptation (DA) aims to enable a learning model trained from a source domain to generalize well on a target domain, despite the mismatch of data distributions between the two domains. State-of-the-art DA methods have so far focused on the search of a latent shared feature space where source and target domain data can be aligned either statistically and/or geometrically. In this paper, we propose a novel unsupervised DA method, namely Discriminative Noise Robust Sparse Orthogonal Label Regression-based Domain Adaptation (DOLL-DA). The proposed DOLL-DA derives from a novel integrated model which searches a shared feature subspace where source and target domain data are, through optimization of some repulse force terms, discriminatively aligned statistically, while at same time regresses orthogonally data labels thereof using a label embedding trick. Furthermore, in minimizing a novel Noise Robust Sparse Orthogonal Label Regression(NRS_OLR) term, the proposed model explicitly accounts for data outliers to avoid negative transfer and introduces the property of sparsity when regressing data labels. Due to the character restriction. Please read our detailed abstract in our paper.

cs.CV↗

arXiv2020

Taking Control of Intra-class Variation in Conditional GANs Under Weak Supervision

Generative Adversarial Networks (GANs) are able to learn mappings between simple, relatively low-dimensional, random distributions and points on the manifold of realistic images in image-space. The semantics of this mapping, however, are typically entangled such that meaningful image properties cannot be controlled independently of one another. Conditional GANs (cGANs) provide a potential solution to this problem, allowing specific semantics to be enforced during training. This solution, however, depends on the availability of precise labels, which are sometimes difficult or near impossible to obtain, e.g. labels representing lighting conditions or describing the background. In this paper we introduce a new formulation of the cGAN that is able to learn disentangled, multivariate models of semantically meaningful variation and which has the advantage of requiring only the weak supervision of binary attribute labels. For example, given only labels of ambient / non-ambient lighting, our method is able to learn multivariate lighting models disentangled from other factors such as the identity and pose. We coin the method intra-class variation isolation (IVI) and the resulting network the IVI-GAN. We evaluate IVI-GAN on the CelebA dataset and on synthetic 3D morphable model data, learning to disentangle attributes such as lighting, pose, expression, and even the background.

cs.CV↗

arXiv2020

Robustness of Facial Recognition to GAN-based Face-morphing Attacks

Face-morphing attacks have been a cause for concern for a number of years. Striving to remain one step ahead of attackers, researchers have proposed many methods of both creating and detecting morphed images. These detection methods, however, have generally proven to be inadequate. In this work we identify two new, GAN-based methods that an attacker may already have in his arsenal. Each method is evaluated against state-of-the-art facial recognition (FR) algorithms and we demonstrate that improvements to the fidelity of FR algorithms do lead to a reduction in the success rate of attacks provided morphed images are considered when setting operational acceptance thresholds.

cs.CV↗

arXiv2020

An Assessment of GANs for Identity-related Applications

Generative Adversarial Networks (GANs) are now capable of producing synthetic face images of exceptionally high visual quality. In parallel to the development of GANs themselves, efforts have been made to develop metrics to objectively assess the characteristics of the synthetic images, mainly focusing on visual quality and the variety of images. Little work has been done, however, to assess overfitting of GANs and their ability to generate new identities. In this paper we apply a state of the art biometric network to various datasets of synthetic images and perform a thorough assessment of their identity-related characteristics. We conclude that GANs can indeed be used to generate new, imagined identities meaning that applications such as anonymisation of image sets and augmentation of training datasets with distractor images are viable applications. We also assess the ability of GANs to disentangle identity from other image characteristics and propose a novel GAN triplet loss that we show to improve this disentanglement.

cs.CV↗

arXiv2020

Anisotropic ultrafast spin/valley dynamics in WTe2 films

WTe2 Weyl semimetal hosts the natural broken inversion symmetry and strong spin orbit coupling, making it promising for exotic spin/valley dynamics within a picosecond timescale. Here, we unveil an anisotropic ultrafast spin/valley dynamics in centimeter-scale, single-crystalline Td-WTe2 films using a femtosecond pump-probe technique at room temperature. We observe a transient (~0.8 ps) intra-valley transition and a subsequent polarization duration (~5 ps) during the whole spin/valley relaxation process. Furthermore, the relaxation exhibits the remarkable anisotropy of approximately six-fold and two-fold symmetries due to the intrinsic anisotropy along the crystalline orientation and the extrinsic matrix element effect, respectively. Our results offer a prospect for the ultrafast manipulation of spin/valleytronics in topological quantum materials for dissipationless high-speed spin/valleytronic devices.

cond-mat.mtrl-sci↗

arXiv2020

Bayesian Optimization for Developmental Robotics with Meta-Learning by Parameters Bounds Reduction

In robotics, methods and softwares usually require optimizations of hyperparameters in order to be efficient for specific tasks, for instance industrial bin-picking from homogeneous heaps of different objects. We present a developmental framework based on long-term memory and reasoning modules (Bayesian Optimisation, visual similarity and parameters bounds reduction) allowing a robot to use meta-learning mechanism increasing the efficiency of such continuous and constrained parameters optimizations. The new optimization, viewed as a learning for the robot, can take advantage of past experiences (stored in the episodic and procedural memories) to shrink the search space by using reduced parameters bounds computed from the best optimizations realized by the robot with similar tasks of the new one (e.g. bin-picking from an homogenous heap of a similar object, based on visual similarity of objects stored in the semantic memory). As example, we have confronted the system to the constrained optimizations of 9 continuous hyperparameters for a professional software (Kamido) in industrial robotic arm bin-picking tasks, a step that is needed each time to handle correctly new object. We used a simulator to create bin-picking tasks for 8 different objects (7 in simulation and one with real setup, without and with meta-learning with experiences coming from other similar objects) achieving goods results despite a very small optimization budget, with a better performance reached when meta-learning is used (84.3% vs 78.9% of success overall, with a small budget of 30 iterations for each optimization) for every object tested (p-value=0.036).

cs.RO↗

arXiv2020

1.4-mJ High Energy Terahertz Radiation from Lithium Niobates

Free-space super-strong terahertz (THz) electromagnetic fields offer multifaceted capabilities for reaching extreme nonlinear THz optics, accelerating and manipulating charged particles, and realizing other fascinating applications. However, the lack of powerful solid-state THz sources with single pulse energy >1 mJ is impeding the proliferation of extreme THz applications. The fundamental challenge lies in hard to achieve high efficiency due to high intensity pumping caused crystal damage, linear absorption and nonlinear distortion induced short effective interaction length, and so on. Here, through cryogenically cooling the crystals, delicately tailoring the pump laser spectra, chirping the pump pulses, and magnifying the laser energies, we first successfully realized the generation of 1.4-mJ THz pulses lithium niobates under the excitation of 214-mJ femtosecond laser pulses via tilted pulse front technique. The 800 nm-to-THz energy conversion efficiency reached 0.7%, and a free-space THz peak electric and magnetic fields reached 6.3 MV/cm and 2.1 Tesla. Our numerical simulations based on a frequencydomain second-order nonlinear wave equation under slowly varying envelope approximation reproduced the experimental optimization processes. To show the capability of this super-strong THz source, nonlinear absorption due to field-induced intervalley scattering effect in high conductive silicon induced by strong THz electric field was demonstrated. Such a high energy THz source with a relatively low peak frequency is very appropriate not only for electron acceleration towards table-top X-ray sources but also for extreme THz science and nonlinear applications.

physics.optics↗

arXiv2020

Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image

Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, outlining unoccluded instances by decoding a deep encoder becomes difficult, due to the translation invariance of convolutional layers and the lack of complexity in the decoder. We therefore propose a multicameral design composed of subtask-specific lightweight decoder and encoder-decoder units, coupled in cascade to encourage subtask-specific feature reuse and enforce a learning path within the decoding process. Furthermore, the state-of-the-art datasets for occlusion-aware instance segmentation contain real images with few instances and occlusions mostly due to objects occluding the background, unlike dense object layouts. We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets. Our extensive experiments on Mikado and public datasets show that ordinal multiscale units within the decoding process prove more effective than state-of-the-art design patterns for capturing position-sensitive representations. We also show that Mikado is plausible with respect to real-world problems, in the sense that it enables the learning of performance-enhancing representations transferable to real images, while drastically reducing the need of hand-made annotations for finetuning. The proposed dataset will be made publicly available.

cs.CV↗

arXiv2020

Breaking Batch Normalization for better explainability of Deep Neural Networks through Layer-wise Relevance Propagation

The lack of transparency of neural networks stays a major break for their use. The Layerwise Relevance Propagation technique builds heat-maps representing the relevance of each input in the model s decision. The relevance spreads backward from the last to the first layer of the Deep Neural Network. Layer-wise Relevance Propagation does not manage normalization layers, in this work we suggest a method to include normalization layers. Specifically, we build an equivalent network fusing normalization layers and convolutional or fully connected layers. Heatmaps obtained with our method on MNIST and CIFAR 10 datasets are more accurate for convolutional layers. Our study also prevents from using Layerwise Relevance Propagation with networks including a combination of connected layers and normalization layer.

cs.LG↗

arXiv2019

Observation of Shubnikov-de Haas Oscillations in Large-Scale Weyl Semimetal WTe2 Films

Topological Weyl semimetal WTe2 with large-scale film form has a promising prospect for new-generation spintronic devices. However, it remains a hard task to suppress the defect states in large-scale WTe2 films due to the chemical nature. Here, we significantly improve the crystalline quality and remove the Te vacancies in WTe2 films by post annealing. We observe the distinct Shubnikov-de Haas quantum oscillations in WTe2 films. The nontrivial Berry phase can be revealed by Landau fan diagram analysis. The Hall mobility of WTe2 films can reach 1245 cm2V-1s-1 and 1423 cm2V-1s-1 for holes and electrons with the carrier density of 5 * 10^19 cm^-3 and 2 * 10^19 cm^-3, respectively. Our work provides a feasible route to obtain high-quality Weyl semimetal films for the future topological quantum device applications.

cond-mat.mtrl-sci↗

arXiv2019

Challenging deep image descriptors for retrieval in heterogeneous iconographic collections

This article proposes to study the behavior of recent and efficient state-of-the-art deep-learning based image descriptors for content-based image retrieval, facing a panel of complex variations appearing in heterogeneous image datasets, in particular in cultural collections that may involve multi-source, multi-date and multi-view Permission to make digital

cs.CV↗

arXiv2019

Optical Control of transverse Motion of Ionization injected Electrons in Laser Plasma Wakefield

We demonstrate an all-optical method for controlling the transverse motion of ionization injected electron beam, by utilizing the transversely asymmetrical wakefield via adjusting the shape of the laser focal spot. When the laser spot shape is changed from the circular to the obliquely elliptic in experiment, the electron beam shape becomes from elliptic to three different shapes. The 3D-PIC simulation results agree well with experiment, and it shows the trajectories of the accelerated electrons change from undulation to helix. Such an all-optical method could be useful for convenient control of the transverse motion of an electron beam which results in synchrotron radiation with orbit angular momentum.

physics.plasm-ph↗

arXiv2019

Toward a Procedural Fruit Tree Rendering Framework for Image Analysis

We propose a procedural fruit tree rendering framework, based on Blender and Python scripts allowing to generate quickly labeled dataset (i.e. including ground truth semantic segmentation). It is designed to train image analysis deep learning methods (e.g. in a robotic fruit harvesting context), where real labeled training datasets are usually scarce and existing synthetic ones are too specialized. Moreover, the framework includes the possibility to introduce parametrized variations in the model (e.g. lightning conditions, background), producing a dataset with embedded Domain Randomization aspect.

cs.CV↗

arXiv2019

Laser Driven Ultra-compact Undulator for Synchrotron Radiation

Laser wakefield accelerators have emerged as a promising candidate for compact synchrotron radiation and even x-ray free electron lasers. Today, to make the electrons emit electromagnetic radiation, the trajectories of laser wakefield accelerated electrons are deflected by transverse wakefield, counter-propagating laser field or external permanent magnet insertion device. Here, we propose a novel type of undulator which has a few hundred microns of period and tens of Tesla of magnetic field. The undulator consists of a bifilar capacitor-coil target which sustains strong discharge current that generates helical magnetic field around the coil axis when irradiated by a high energy laser. Coupling this undulator with state-of-the-art laser wakefield accelerators can, simultaneously, produce ultra-bright quasi-monochromatic x-rays with tunable energy ranging 5-250 keV and optimize the free electron laser parameter and gain length compared with permanent magnet based undulator. This concept may pave a path toward ultra-compact synchrotron radiation and even x-ray free electron lasers.

physics.acc-ph↗

arXiv2018

Image-based Natural Language Understanding Using 2D Convolutional Neural Networks

We propose a new approach to natural language understanding in which we consider the input text as an image and apply 2D Convolutional Neural Networks to learn the local and global semantics of the sentences from the variations ofthe visual patterns of words. Our approach demonstrates that it is possible to get semantically meaningful features from images with text without using optical character recognition and sequential processing pipelines, techniques that traditional Natural Language Understanding algorithms require. To validate our approach, we present results for two applications: text classification and dialog modeling. Using a 2D Convolutional Neural Network, we were able to outperform the state-of-art accuracy results of non-Latin alphabet-based text classification and achieved promising results for eight text classification datasets. Furthermore, our approach outperformed the memory networks when using out of vocabulary entities fromtask 4 of the bAbI dialog dataset.

cs.CL↗