Search arXiv⌕ Search

arXiv subjects

Cheng Peng

Publications and source records attributed to Cheng Peng.

At least 199 records · Page 11Linked to original sources
arXiv2020

Unsupervised Many-to-Many Image-to-Image Translation Across Multiple Domains

Unsupervised multi-domain image-to-image translation aims to synthesis images among multiple domains without labeled data, which is more general and complicated than one-to-one image mapping. However, existing methods mainly focus on reducing the large costs of modeling and do not pay enough attention to the quality of generated images. In some target domains, their translation results may not be expected or even it has model collapse. To improve the image quality, we propose an effective many-to-many mapping framework for unsupervised multi-domain image-to-image translation. There are two key aspects in our method. The first is a proposed many-to-many architecture with only one domain-shared encoder and several domain-specialized decoders to effectively and simultaneously translate images across multiple domains. The second is two proposed constraints extended from one-to-one mappings to further help improve the generation. All the evaluations demonstrate our framework is superior to existing methods and provides an effective solution for multi-domain image-to-image translation.

cs.CV↗
arXiv2020

Ellipse R-CNN: Learning to Infer Elliptical Object from Clustering and Occlusion

Images of heavily occluded objects in cluttered scenes, such as fruit clusters in trees, are hard to segment. To further retrieve the 3D size and 6D pose of each individual object in such cases, bounding boxes are not reliable from multiple views since only a little portion of the object's geometry is captured. We introduce the first CNN-based ellipse detector, called Ellipse R-CNN, to represent and infer occluded objects as ellipses. We first propose a robust and compact ellipse regression based on the Mask R-CNN architecture for elliptical object detection. Our method can infer the parameters of multiple elliptical objects even they are occluded by other neighboring objects. For better occlusion handling, we exploit refined feature regions for the regression stage, and integrate the U-Net structure for learning different occlusion patterns to compute the final detection score. The correctness of ellipse regression is validated through experiments performed on synthetic data of clustered ellipses. We further quantitatively and qualitatively demonstrate that our approach outperforms the state-of-the-art model (i.e., Mask R-CNN followed by ellipse fitting) and its three variants on both synthetic and real datasets of occluded and clustered elliptical objects.

cs.CV↗
arXiv2020

Ensemble averages, Poisson processes and Microstates

We consider ensemble averaged theories with discrete random variables. We propose a suitable measure to do the ensemble average. We also provide a mathematical description of such ensemble averages of theories in terms of Poisson point processes. Moreover, we demonstrate that averaging theories of this type has an equivalent description as tracing over parts of the microscopic degrees of freedom in a suitable continuous limit of a single microscopic theory. The results from both approaches can be identified with Liouville gravity, of which we further address some implications on the microscopic theory, including venues to look for quantum effects from the view point of the averaged theory. Generalizations to other point processes are also discussed.

hep-th↗
arXiv2020

A Multi-Task Incremental Learning Framework with Category Name Embedding for Aspect-Category Sentiment Analysis

(T)ACSA tasks, including aspect-category sentiment analysis (ACSA) and targeted aspect-category sentiment analysis (TACSA), aims at identifying sentiment polarity on predefined categories. Incremental learning on new categories is necessary for (T)ACSA real applications. Though current multi-task learning models achieve good performance in (T)ACSA tasks, they suffer from catastrophic forgetting problems in (T)ACSA incremental learning tasks. In this paper, to make multi-task learning feasible for incremental learning, we proposed Category Name Embedding network (CNE-net). We set both encoder and decoder shared among all categories to weaken the catastrophic forgetting problem. Besides the origin input sentence, we applied another input feature, i.e., category name, for task discrimination. Our model achieved state-of-the-art on two (T)ACSA benchmark datasets. Furthermore, we proposed a dataset for (T)ACSA incremental learning and achieved the best performance compared with other strong baselines.

cs.CL↗
arXiv2020

Few-body solutions under spin-exchange interaction: magnetic bound state and the Kondo screening effect

Motivated by recent progresses on ultracold alkaline-earth atoms towards the goal of simulating Kondo physics, in this work we exactly solve the few-body problem of one and two trapped fermions in one dimension interacting with a localized impurity under tunable spin-exchange interaction. It is found that depending on the sign of the spin-exchange coupling, ferromagnetic(FM) or anti-ferromagnetic(AFM), the attractive and repulsive branches can hold different magnetic structures. For the two fermions case, we demonstrate the Kondo screening effect for the attractive branch with AFM coupling, and show that such screening is absent for the ground state with FM coupling. Moreover, we find a sequence of FM upper branches in the AFM coupling side. These FM states are orthogonal to all other attractive branches and their wave functions feature a full spin-charge separation. The effect of an additional contact interaction and the extension of our results to many particles are also discussed. This work reveals the intriguing physics uniquely associated with the spin-exchange interaction in the few-body point of view, which are promisingly to be explored in the experiment of ultracold alkaline-earth atoms.

cond-mat.quant-gas↗
arXiv2020

Evidence of pair-density wave in doping Kitaev spin liquid on the honeycomb lattice

We study the effects of doping the Kitaev model on the honeycomb lattice where the spins interact via the bond-directional interaction $J_K$, which is known to have a quantum spin liquid as its exact ground state. The effect of hole doping is studied within the $t$-$J_K$ model on a three-leg cylinder using density-matrix renormalization group. Upon light doping, we find that the ground state of the system has quasi-long-range charge-density-wave correlations but short-range single-particle correlations. The dominant pairing channel is the even-parity superconducting pair-pair correlations with $d$-wave-like symmetry, which oscillate in sign as a function of separation with a period equal to that of the spin-density wave and two times the charge-density wave. Although these correlations fall rapidly (possibly exponentially) at long distances, this is never-the-less the first example where a pair-density wave is the strongest SC order on a bipartite lattice. Our results may be relevant to ${\rm Na_2IrO_3}$ and $α$-${\rm RuCl_3}$ upon doping.

cond-mat.str-el↗
arXiv2020

Potential Field: Interpretable and Unified Representation for Trajectory Prediction

Predicting an agent's future trajectory is a challenging task given the complicated stimuli (environmental/inertial/social) of motion. Prior works learn individual stimulus from different modules and fuse the representations in an end-to-end manner, which makes it hard to understand what are actually captured and how they are fused. In this work, we borrow the notion of potential field from physics as an interpretable and unified representation to model all stimuli. This allows us to not only supervise the intermediate learning process, but also have a coherent method to fuse the information of different sources. From the generated potential fields, we further estimate future motion direction and speed, which are modeled as Gaussian distributions to account for the multi-modal nature of the problem. The final prediction results are generated by recurrently moving past location based on the estimated motion direction and speed. We show state-of-the-art results on the ETH, UCY, and Stanford Drone datasets.

cs.CV↗
arXiv2020

SAINT: Spatially Aware Interpolation NeTwork for Medical Slice Synthesis

Deep learning-based single image super-resolution (SISR) methods face various challenges when applied to 3D medical volumetric data (i.e., CT and MR images) due to the high memory cost and anisotropic resolution, which adversely affect their performance. Furthermore, mainstream SISR methods are designed to work over specific upsampling factors, which makes them ineffective in clinical practice. In this paper, we introduce a Spatially Aware Interpolation NeTwork (SAINT) for medical slice synthesis to alleviate the memory constraint that volumetric data poses. Compared to other super-resolution methods, SAINT utilizes voxel spacing information to provide desirable levels of details, and allows for the upsampling factor to be determined on the fly. Our evaluations based on 853 CT scans from four datasets that contain liver, colon, hepatic vessels, and kidneys show that SAINT consistently outperforms other SISR methods in terms of medical slice synthesis quality, while using only a single model to deal with different upsampling factors.

eess.IV↗
arXiv2019

Idle Time Optimization for Target Assignment and Path Finding in Sortation Centers

In this paper, we study the one-shot and lifelong versions of the Target Assignment and Path Finding problem in automated sortation centers, where each agent needs to constantly assign itself a sorting station, move to its assigned station without colliding with obstacles or other agents, wait in the queue of that station to obtain a parcel for delivery, and then deliver the parcel to a sorting bin. The throughput of such centers is largely determined by the total idle time of all stations since their queues can frequently become empty. To address this problem, we first formalize and study the one-shot version that assigns stations to a set of agents and finds collision-free paths for the agents to their assigned stations. We present efficient algorithms for this task based on a novel min-cost max-flow formulation that minimizes the total idle time of all stations in a fixed time window. We then demonstrate how our algorithms for solving the one-shot problem can be applied to solving the lifelong problem as well. Experimentally, we believe to be the first researchers to consider real-world automated sortation centers using an industrial simulator with realistic data and a kinodynamic model of real robots. On this simulator, we showcase the benefits of our algorithms by demonstrating their efficiency and effectiveness for up to 350 agents.

cs.AI↗
arXiv2019

Anatomy of Deconfinement

In the weak coupling limit of ${\rm SU}(N)$ Yang-Mills theory and the ${\rm O}(N)$ vector model, explicit state counting allows us to demonstrate the existence of a partially deconfined phase: $M$ of $N$ colors deconfine, and $\frac{M}{N}$ gradually grows from zero (confinement) to one (complete deconfinement). We point out that the mechanism admits a simple interpretation in the form of spontaneous breaking of gauge symmetry. In terms of the dual gravity theory, such breaking occurs during the formation of a black hole. We speculate whether the breaking and restoration of gauge symmetry can serve as an alternative definition of the deconfinement transition in theories without center symmetry, such as QCD. We also discuss the role of the color degrees of freedom in the emergence of the bulk geometry in holographic duality.

hep-th↗
arXiv2019

Adaptive View Planning for Aerial 3D Reconstruction

With the proliferation of small aerial vehicles, acquiring close up aerial imagery for high quality reconstruction of complex scenes is gaining importance. We present an adaptive view planning method to collect such images in an automated fashion. We start by sampling a small set of views to build a coarse proxy to the scene. We then present (i)~a method that builds a view manifold for view selection, and (ii) an algorithm to select a sparse set of views. The vehicle then visits these viewpoints to cover the scene, and the procedure is repeated until reconstruction quality converges or a desired level of quality is achieved. The view manifold provides an effective efficiency/quality compromise between using the entire 6 degree of freedom pose space and using a single view hemisphere to select the views. Our results show that, in contrast to existing "explore and exploit" methods which collect only two sets of views, reconstruction quality can be drastically improved by adding a third set. They also indicate that three rounds of data collection is sufficient even for very complex scenes. We compare our algorithm to existing methods in three challenging scenes. We require each algorithm to select the same number of views. Our algorithm generates views which produce the least reconstruction error.

cs.CV↗
arXiv2019

Map as The Hidden Sensor: Fast Odometry-Based Global Localization

Accurate and robust global localization is essential to robotics applications. We propose a novel global localization method that employs the map traversability as a hidden observation. The resulting map-corrected odometry localization is able to provide an accurate belief tensor of the robot state. Our method can be used for blind robots in dark or highly reflective areas. In contrast to odometry drift in long-term, our method using only odometry and the map converges in longterm. Our method can also be integrated with other sensors to boost the localization performance. The algorithm does not have any initial state assumption and tracks all possible robot states at all times. Therefore, our method is global and is robust in the event of ambiguous observations. We parallel each step of our algorithm such that it can be performed in real-time (up to ~ 300 Hz) using GPU. We validate our algorithm in different publicly available floor-plans and show that it is able to converge to the ground truth fast while being robust to ambiguities.

cs.RO↗
arXiv2019

High-Speed Phase-Only Spatial Light Modulators with Two-Dimensional Tunable Microcavity Arrays

Spatial light modulators (SLMs) are central to numerous applications ranging from high-speed displays to adaptive optics, structured illumination microscopy, and holography. After decades of advances, SLM arrays based on liquid crystals can now reach large pixel counts exceeding 10^6 with phase-only modulation with a pixel pitch of less than 10 μm and reflectance around 75%. However, the rather slow modulation speed in such SLMs (below hundreds of Hz) presents limitations for many applications. Here we propose an SLM architecture that can achieve high pixel count with high-resolution phase-only modulation at high speed in excess of GHz. The architecture consists of a tunable two-dimensional array of vertically oriented, one-sided microcavities that are tuned through an electro-optic material such as barium titanate (BTO). We calculate that the optimized microcavity design achieves a π phase shift under an applied bias voltage below 10 V, while maintaining nearly constant reflection amplitude. As two model applications, we consider high-speed 2D beam steering as well as beam forming. The outlined design methodology could also benefit future design of spatial light modulators with other specifications (for example amplitude modulators). This high-speed SLM architecture promises a wide range of new applications ranging from fully tunable metasurfaces to optical computing accelerators, high-speed interconnects, true 2D phased array beam steering, and quantum computing with cold atom arrays.

physics.optics↗
arXiv2019

Towards multi-sequence MR image recovery from undersampled k-space data

Undersampled MR image recovery has been widely studied for accelerated MR acquisition. However, it has been mostly studied under a single sequence scenario, despite the fact that multi-sequence MR scan is common in practice. In this paper, we aim to optimize multi-sequence MR image recovery from undersampled k-space data under an overall time constraint while considering the difference in acquisition time for various sequences. We first formulate it as a constrained optimization problem and then show that finding the optimal sampling strategy for all sequences and the best recovery model at the same time is combinatorial and hence computationally prohibitive. To solve this problem, we propose a blind recovery model that simultaneously recovers multiple sequences, and an efficient approach to find proper combination of sampling strategy and recovery model. Our experiments demonstrate that the proposed method outperforms sequence-wise recovery, and sheds light on how to decide the undersampling strategy for sequences within an overall time budget.

eess.IV↗
arXiv2019

Deep Slice Interpolation via Marginal Super-Resolution, Fusion and Refinement

We propose a marginal super-resolution (MSR) approach based on 2D convolutional neural networks (CNNs) for interpolating an anisotropic brain magnetic resonance scan along the highly under-sampled direction, which is assumed to axial without loss of generality. Previous methods for slice interpolation only consider data from pairs of adjacent 2D slices. The possibility of fusing information from the direction orthogonal to the 2D slices remains unexplored. Our approach performs MSR in both sagittal and coronal directions, which provides an initial estimate for slice interpolation. The interpolated slices are then fused and refined in the axial direction for improved consistency. Since MSR consists of only 2D operations, it is more feasible in terms of GPU memory consumption and requires fewer training samples compared to 3D CNNs. Our experiments demonstrate that the proposed method outperforms traditional linear interpolation and baseline 2D/3D CNN-based approaches. We conclude by showcasing the method's practical utility in estimating brain volumes from under-sampled brain MR scans through semantic segmentation.

eess.IV↗
arXiv2019

Lecture Notes of Tensor Network Contractions

Tensor network (TN), a young mathematical tool of high vitality and great potential, has been undergoing extremely rapid developments in the last two decades, gaining tremendous success in condensed matter physics, atomic physics, quantum information science, statistical physics, and so on. In this lecture notes, we focus on the contraction algorithms of TN as well as some of the applications to the simulations of quantum many-body systems. Starting from basic concepts and definitions, we first explain the relations between TN and physical problems, including the TN representations of classical partition functions, quantum many-body states (by matrix product state, tree TN, and projected entangled pair state), time evolution simulations, etc. These problems, which are challenging to solve, can be transformed to TN contraction problems. We present then several paradigm algorithms based on the ideas of the numerical renormalization group and/or boundary states, including density matrix renormalization group, time-evolving block decimation, coarse-graining/corner tensor renormalization group, and several distinguished variational algorithms. Finally, we revisit the TN approaches from the perspective of multi-linear algebra (also known as tensor algebra or tensor decompositions) and quantum simulation. Despite the apparent differences in the ideas and strategies of different TN algorithms, we aim at revealing the underlying relations and resemblances in order to present a systematic picture to understand the TN contraction approaches.

physics.comp-ph↗
arXiv2019

DuDoNet: Dual Domain Network for CT Metal Artifact Reduction

Computed tomography (CT) is an imaging modality widely used for medical diagnosis and treatment. CT images are often corrupted by undesirable artifacts when metallic implants are carried by patients, which creates the problem of metal artifact reduction (MAR). Existing methods for reducing the artifacts due to metallic implants are inadequate for two main reasons. First, metal artifacts are structured and non-local so that simple image domain enhancement approaches would not suffice. Second, the MAR approaches which attempt to reduce metal artifacts in the X-ray projection (sinogram) domain inevitably lead to severe secondary artifact due to sinogram inconsistency. To overcome these difficulties, we propose an end-to-end trainable Dual Domain Network (DuDoNet) to simultaneously restore sinogram consistency and enhance CT images. The linkage between the sigogram and image domains is a novel Radon inversion layer that allows the gradients to back-propagate from the image domain to the sinogram domain during training. Extensive experiments show that our method achieves significant improvements over other single domain MAR approaches. To the best of our knowledge, it is the first end-to-end dual-domain network for MAR.

eess.IV↗