arXiv subjects

Kai Xu

Publications and source records attributed to Kai Xu.

At least 271 records · Page 15Linked to original sources

arXiv2023

Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinement

Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry for estimating the poses of different parts, facilitating downstream tasks such as robotic grasping. Existing methods fail when the template and source images have different modalities, cluttered backgrounds or weak textures. They also rarely consider geometric transformations via homographies, which commonly exist even for planar industrial parts. To tackle the challenges, we propose an accurate template matching method based on differentiable coarse-to-fine correspondence refinement. We use an edge-aware module to overcome the domain gap between the mask template and the grayscale image, allowing robust matching. An initial warp is estimated using coarse correspondences based on novel structure-aware information provided by transformers. This initial alignment is passed to a refinement network using references and aligned images to obtain sub-pixel level correspondences which are used to give the final geometric transformation. Extensive evaluation shows that our method is significantly better than state-of-the-art methods and baselines, providing good generalization ability and visually plausible results even on unseen real data.

cs.CV↗

arXiv2023

DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training

A standard hardware bottleneck when training deep neural networks is GPU memory. The bulk of memory is occupied by caching intermediate tensors for gradient computation in the backward pass. We propose a novel method to reduce this footprint - Dropping Intermediate Tensors (DropIT). DropIT drops min-k elements of the intermediate tensors and approximates gradients from the sparsified tensors in the backward pass. Theoretically, DropIT reduces noise on estimated gradients and therefore has a higher rate of convergence than vanilla-SGD. Experiments show that we can drop up to 90\% of the intermediate tensor elements in fully-connected and convolutional layers while achieving higher testing accuracy for Visual Transformers and Convolutional Neural Networks on various tasks (e.g., classification, object detection, instance segmentation). Our code and models are available at https://github.com/chenjoya/dropit.

cs.CV↗

arXiv2023

NIFT: Neural Interaction Field and Template for Object Manipulation

We introduce NIFT, Neural Interaction Field and Template, a descriptive and robust interaction representation of object manipulations to facilitate imitation learning. Given a few object manipulation demos, NIFT guides the generation of the interaction imitation for a new object instance by matching the Neural Interaction Template (NIT) extracted from the demos in the target Neural Interaction Field (NIF) defined for the new object. Specifically, the NIF is a neural field that encodes the relationship between each spatial point and a given object, where the relative position is defined by a spherical distance function rather than occupancies or signed distances, which are commonly adopted by conventional neural fields but less informative. For a given demo interaction, the corresponding NIT is defined by a set of spatial points sampled in the demo NIF with associated neural features. To better capture the interaction, the points are sampled on the Interaction Bisector Surface (IBS), which consists of points that are equidistant to the two interacting objects and has been used extensively for interaction representation. With both point selection and pointwise features defined for better interaction encoding, NIT effectively guides the feature matching in the NIFs of the new object instances such that the relative poses are optimized to realize the manipulation while imitating the demo interactions. Experiments show that our NIFT solution outperforms state-of-the-art imitation learning methods for object manipulation and generalizes better to objects from new categories.

cs.RO↗

arXiv2023

Modelling the performance of delivery vehicles across urban micro-regions to accelerate the transition to cargo-bike logistics

Light goods vehicles (LGV) used extensively in the last mile of delivery are one of the leading polluters in cities. Cargo-bike logistics has been put forward as a high impact candidate for replacing LGVs, with experts estimating over half of urban van deliveries being replaceable by cargo bikes, due to their faster speeds, shorter parking times and more efficient routes across cities. By modelling the relative delivery performance of different vehicle types across urban micro-regions, machine learning can help operators evaluate the business and environmental impact of adding cargo-bikes to their fleets. In this paper, we introduce two datasets, and present initial progress in modelling urban delivery service time (e.g. cruising for parking, unloading, walking). Using Uber's H3 index to divide the cities into hexagonal cells, and aggregating OpenStreetMap tags for each cell, we show that urban context is a critical predictor of delivery performance.

cs.LG↗

arXiv2023

Edge Preserving Implicit Surface Representation of Point Clouds

Learning implicit surface directly from raw data recently has become a very attractive representation method for 3D reconstruction tasks due to its excellent performance. However, as the raw data quality deteriorates, the implicit functions often lead to unsatisfactory reconstruction results. To this end, we propose a novel edge-preserving implicit surface reconstruction method, which mainly consists of a differentiable Laplican regularizer and a dynamic edge sampling strategy. Among them, the differential Laplican regularizer can effectively alleviate the implicit surface unsmoothness caused by the point cloud quality deteriorates; Meanwhile, in order to reduce the excessive smoothing at the edge regions of implicit suface, we proposed a dynamic edge extract strategy for sampling near the sharp edge of point cloud, which can effectively avoid the Laplacian regularizer from smoothing all regions. Finally, we combine them with a simple regularization term for robust implicit surface reconstruction. Compared with the state-of-the-art methods, experimental results show that our method significantly improves the quality of 3D reconstruction results. Moreover, we demonstrate through several experiments that our method can be conveniently and effectively applied to some point cloud analysis tasks, including point cloud edge feature extraction, normal estimation,etc.

cs.CV↗

arXiv2022

Non-Ellipsoidal Gravity-Based Definitions of Planetary Surface Area and Other Geodetic Measures

This paper introduces new definitions of common geodetic measures on a planetary surface (namely surface area, path length, and mean value or other statistical parameters of a surface function) that are not based on a datum such as a reference ellipsoid. Instead, the so-called datumless geodetic measures are based on physically meaningful formulations that rely only on the actual planetary surface and gravity. The datumless measures provide universally standardized measurements on any terrestrial object, including non-ellipsoidal asteroids and comets. Conveniently, on fairly round planets such as Earth and Mars, the datumless measures yield very similar values as corresponding geodetic measures on a reference ellipsoid. Like their ellipsoidal counterparts, the datumless measures quantify area and length in the familiar "bird's-eye view" or "horizontal, normal-to-gravity" sense. Far from being purely theoretical, the datumless measures can be approximated in GIS software using a digital elevation model and a gravity model such as a geoid.

astro-ph.EP↗

arXiv2022

ScQ cloud quantum computation for generating Greenberger-Horne-Zeilinger states of up to 10 qubits

In this study, we introduce an online public quantum computation platform, named as ScQ, based on a 1D array of a 10-qubit superconducting processor. Single-qubit rotation gates can be performed on each qubit. Controlled-NOT gates between nearest-neighbor sites on the 1D array of 10 qubits are available. We show the online preparation and verification of Greenberger-Horne-Zeilinger states of up to 10 qubits through this platform for all possible blocks of qubits in the chain. The graphical user interface and quantum assembly language methods are presented to achieve the above tasks, which rely on a parameter scanning feature implemented on ScQ. The performance of this quantum computation platform, such as fidelities of logic gates and details of the superconducting device, are presented.

quant-ph↗

arXiv2022

Multi-resolution Monocular Depth Map Fusion by Self-supervised Gradient-based Composition

Monocular depth estimation is a challenging problem on which deep neural networks have demonstrated great potential. However, depth maps predicted by existing deep models usually lack fine-grained details due to the convolution operations and the down-samplings in networks. We find that increasing input resolution is helpful to preserve more local details while the estimation at low resolution is more accurate globally. Therefore, we propose a novel depth map fusion module to combine the advantages of estimations with multi-resolution inputs. Instead of merging the low- and high-resolution estimations equally, we adopt the core idea of Poisson fusion, trying to implant the gradient domain of high-resolution depth into the low-resolution depth. While classic Poisson fusion requires a fusion mask as supervision, we propose a self-supervised framework based on guided image filtering. We demonstrate that this gradient-based composition performs much better at noisy immunity, compared with the state-of-the-art depth map fusion method. Our lightweight depth fusion is one-shot and runs in real-time, making our method 80X faster than a state-of-the-art depth fusion method. Quantitative evaluations demonstrate that the proposed method can be integrated into many fully convolutional monocular depth estimation backbones with a significant performance boost, leading to state-of-the-art results of detail enhancement on depth maps.

cs.CV↗

arXiv2022

Holography and the KKLT Scenario

The KKLT scenario, one of the few ideas to realize dS vacua in string theory, consists of two steps: the first involves the construction of a supersymmetric AdS vacuum with a small negative cosmological constant, and the second involves breaking supersymmetry and uplifting the energy to achieve dS. In this paper we use conventional holography to argue why it is not possible to complete the first step. We obtain this by putting a bound on the central charge of the dual theory which involves branes wrapping special Lagrangian cycles in CY 4-folds. We find that $l_{\rm AdS}^2 \lesssim χ(CY_4)$. Since $l_{\rm species}^2\gtrsim χ(CY_4)$ this leads to $l_{\rm AdS}/l_{\rm species}\lesssim 1$ leading at best to a highly curved AdS which is beyond the validity of the EFT.

hep-th↗

arXiv2022

A possible interpretation of $Λ$ baryon spectrum with pentaquark components

The $Λ$ baryon spectrum is studied within the SU(3) flavor symmetry in a constituent quark model. We found that it is rather difficult to accommodate some negative-parity $Λ$ resonances as single $q^2s$ ($q = u,\,d$ quarks) states in the conventional three-quark picture. The ground $q^3s\bar q$ pentaquark mass spectrum is evaluated and a possible interpretation is proposed in the work: the observed $Λ(1405)1/2^{-}$, $Λ(1670)1/2^{-}$ and $Λ(1800)1/2^{-}$ are three-state mixtures of two $p$-wave $q^2s$ states and one ground $q^3s\bar q$ pentaquark state, so are the $Λ(1520)3/2^{-}$, $Λ(1690)3/2^{-}$ and $Λ(2050)3/2^{-}$ resonances.

hep-ph↗

arXiv2022

Variational Quantum Computation of Molecular Linear Response Properties on a Superconducting Quantum Processor

Simulating response properties of molecules is crucial for interpreting experimental spectroscopies and accelerating materials design. However, it remains a long-standing computational challenge for electronic structure methods on classical computers. While quantum computers hold the promise to solve this problem more efficiently in the long run, existing quantum algorithms requiring deep quantum circuits are infeasible for near-term noisy quantum processors. Here, we introduce a pragmatic variational quantum response (VQR) algorithm for response properties, which circumvents the need for deep quantum circuits. Using this algorithm, we report the first simulation of linear response properties of molecules including dynamic polarizabilities and absorption spectra on a superconducting quantum processor. Our results indicate that a large class of important dynamical properties such as Green's functions are within the reach of near-term quantum hardware using this algorithm in combination with suitable error mitigation techniques.

quant-ph↗

arXiv2022

6DOF Pose Estimation of a 3D Rigid Object based on Edge-enhanced Point Pair Features

The point pair feature (PPF) is widely used for 6D pose estimation. In this paper, we propose an efficient 6D pose estimation method based on the PPF framework. We introduce a well-targeted down-sampling strategy that focuses more on edge area for efficient feature extraction of complex geometry. A pose hypothesis validation approach is proposed to resolve the symmetric ambiguity by calculating edge matching degree. We perform evaluations on two challenging datasets and one real-world collected dataset, demonstrating the superiority of our method on pose estimation of geometrically complex, occluded, symmetrical objects. We further validate our method by applying it to simulated punctures.

cs.CV↗

arXiv2022

Observation of entanglement negativity transition of pseudo-random mixed states

Multipartite entanglement is a key resource for quantum computation. It is expected theoretically that entanglement transition may happen for multipartite random quantum states, however, which is still absent experimentally. Here, we report the observation of entanglement transition quantified by negativity using a fully connected 20-qubit superconducting processor. We implement multi-layer pseudo-random circuits to generate pseudo-random pure states of 7 to 15 qubits. Then, we investigate negativity spectra of reduced density matrices obtained by quantum state tomography for 6 qubits.Three different phases can be identified by calculating logarithmic negativities based on the negativity spectra. We observe the phase transitions by changing the sizes of environment and subsystems. The randomness of our circuits can be also characterized by quantifying the distance between the distribution of output bit-string probabilities and Porter-Thomas distribution. Our simulator provides a powerful tool to generate random states and understand the entanglement structure for multipartite quantum systems.

quant-ph↗

arXiv2022

Decoupling Features and Coordinates for Few-shot RGB Relocalization

Cross-scene model adaption is crucial for camera relocalization in real scenarios. It is often preferable that a pre-learned model can be fast adapted to a novel scene with as few training samples as possible. The existing state-of-the-art approaches, however, can hardly support such few-shot scene adaption due to the entangling of image feature extraction and scene coordinate regression. To address this issue, we approach camera relocalization with a decoupled solution where feature extraction, coordinate regression, and pose estimation are performed separately. Our key insight is that feature encoder used for coordinate regression should be learned by removing the distracting factor of coordinate systems, such that feature encoder is learned from multiple scenes for general feature representation and more important, view-insensitive capability. With this feature prior, and combined with a coordinate regressor, few-shot observations in a new scene are much easier to connect with the 3D world than the one with existing integrated solution. Experiments have shown the superiority of our approach compared to the state-of-the-art methods, producing higher accuracy on several scenes with diverse visual appearance and viewpoint distribution.

cs.CV↗

arXiv2022

Natural selection from the perspective of mathematical and physical laws

The theory of evolution by natural selection cannot be used to evaluate the truth value of the following proposition: Through evolution, there exists at least one species that can adapt to any one given environment. To address this issue, this study attempted to define natural selection from the perspective of mathematical and physical laws. This study roughly classified biological activities into molecular, cellular, individual, ecological, and biogeochemical (atomic) levels according to scale and complexity, and selected typical phenomena from each level to analyze the relationship between adaptive evolution and several laws of mathematics and physics. Then, we proposed that natural selection favors heritable variations that allows organisms to better use and/or hide the laws in a certain environment. Reproductive advantage is by far the most obvious consequence of natural selection. Moreover, adaptive evolution can lead to the emergence of laws that ensures that each law only controls some properties of organisms. This study found that organisms significantly influence themselves in all five levels of biological activities, and the whole biosphere can be considered as a huge and evolution-driven feedback loop. Organisms can carry more laws than non-living matter, but the carrying capacity is limited. Therefore, this study's findings suggest that adaptive evolution makes organisms subject to more laws of mathematics and physics until the highest carrying capacity is reached.

physics.bio-ph↗

arXiv2022

Probing Operator Spreading via Floquet Engineering in a Superconducting Circuit

Operator spreading, often characterized by out-of-time-order correlators (OTOCs), is one of the central concepts in quantum many-body physics. However, measuring OTOCs is experimentally challenging due to the requirement of reversing the time evolution of systems. Here we apply Floquet engineering to investigate operator spreading in a superconducting 10-qubit chain. Floquet engineering provides an effective way to tune the coupling strength between nearby qubits, which is used to demonstrate quantum walks with tunable couplings, reversed time evolution, and the measurement of OTOCs. A clear light-cone-like operator propagation is observed in the system with multiple excitations, and has a nearly equal velocity as the single-particle quantum walk. For the butterfly operator that is nonlocal (local) under the Jordan-Wigner transformation, the OTOCs show distinct behaviors with (without) a signature of information scrambling in the near integrable system.

quant-ph↗

arXiv2022

The complex mKdV equation with step-like initial data: Large time asymptotic analysis

In this paper, we study large-time asymptotics for the complex modified Korteveg-de Vries equation \begin{equation} u_t + \frac{1}{2}u_{xxx}+3|u|^2 u_x=0, \end{equation} with the step-like initial data \begin{equation} u(x,0)=u_0(x)= \begin{cases} 0, & {x \ge 0,}\\ A e^{iBx}, &{x < 0.} \end{cases} \end{equation} It is shown that the step-like initial problem can be described by a matrix Riemann-Hilbert problem. We apply the steepest descent method to obtain different large-time asymptotics in the the Zakharov-Manakov region, a plane wave region and a slow decay region.

math.AP↗

arXiv2022

HybridGNN: Learning Hybrid Representation in Multiplex Heterogeneous Networks

Recently, graph neural networks have shown the superiority of modeling the complex topological structures in heterogeneous network-based recommender systems. Due to the diverse interactions among nodes and abundant semantics emerging from diverse types of nodes and edges, there is a bursting research interest in learning expressive node representations in multiplex heterogeneous networks. One of the most important tasks in recommender systems is to predict the potential connection between two nodes under a specific edge type (i.e., relationship). Although existing studies utilize explicit metapaths to aggregate neighbors, practically they only consider intra-relationship metapaths and thus fail to leverage the potential uplift by inter-relationship information. Moreover, it is not always straightforward to exploit inter-relationship metapaths comprehensively under diverse relationships, especially with the increasing number of node and edge types. In addition, contributions of different relationships between two nodes are difficult to measure. To address the challenges, we propose HybridGNN, an end-to-end GNN model with hybrid aggregation flows and hierarchical attentions to fully utilize the heterogeneity in the multiplex scenarios. Specifically, HybridGNN applies a randomized inter-relationship exploration module to exploit the multiplexity property among different relationships. Then, our model leverages hybrid aggregation flows under intra-relationship metapaths and randomized exploration to learn the rich semantics. To explore the importance of different aggregation flow and take advantage of the multiplexity property, we bring forward a novel hierarchical attention module which leverages both metapath-level attention and relationship-level attention. Extensive experimental results suggest that HybridGNN achieves the best performance compared to several state-of-the-art baselines.

cs.LG↗