Search

In this paper, we address a recent trend in robotic home appliances to include vision systems on personal devices, capable of personalizing the appliances on the fly. In particular, we formulate and address an important technical task of personal object search, which involves localization and identification of personal items of interest on images captured by robotic appliances, with each item referenced only by a few annotated images. The task is crucial for robotic home appliances and mobile systems, which need to process personal visual scenes or to operate with particular personal objects (e.g., for grasping or navigation). In practice, personal object search presents two main technical challenges. First, a robot vision system needs to be able to distinguish between many fine-grained classes, in the presence of occlusions and clutter. Second, the strict resource requirements for the on-device system restrict the usage of most state-of-the-art methods for few-shot learning and often prevent on-device adaptation. In this work, we propose Swiss DINO: a simple yet effective framework for one-shot personal object search based on the recent DINOv2 transformer model, which was shown to have strong zero-shot generalization properties. Swiss DINO handles challenging on-device personalized scene understanding requirements and does not require any adaptation training. We show significant improvement (up to 55%) in segmentation and recognition accuracy compared to the common lightweight solutions, and significant footprint reduction of backbone inference time (up to 100x) and GPU consumption (up to 10x) compared to the heavy transformer-based solutions., Comment: 8 pages, 2 figures, accepted to IROS2024

The rapid advancement of wireless communication technologies has precipitated an unprecedented demand for high data rates, extremely low latency, and ubiquitous connectivity. In order to achieve these goals, stacked intelligent metasurfaces (SIM) has been developed as a novel solution to perform advanced signal processing tasks directly in the electromagnetic wave domain, thus achieving ultra-fast computing speed and reducing hardware complexity. This article provides an overview of the SIM technology by discussing its hardware architectures, advantages, and potential applications for wireless sensing and communication. Specifically, we explore the utilization of SIMs in enabling wave-domain beamforming, channel modeling and estimation in SIM-assisted communication systems. Furthermore, we elaborate on the potential of utilizing a SIM to build a hybrid optical-electronic neural network (HOENN) and demonstrate its efficacy by examining two case studies: disaster monitoring and direction-of-arrival estimation. Finally, we identify key implementation challenges, including practical hardware imperfections, efficient SIM configuration for realizing wave-domain signal processing, and performance analysis to motivate future research on this important and far-reaching topic., Comment: 8 pages, 5 figures, 1 table

We present SPEAR, a continuous receiver-to-receiver acoustic neural warping field for spatial acoustic effects prediction in an acoustic 3D space with a single stationary audio source. Unlike traditional source-to-receiver modelling methods that require prior space acoustic properties knowledge to rigorously model audio propagation from source to receiver, we propose to predict by warping the spatial acoustic effects from one reference receiver position to another target receiver position, so that the warped audio essentially accommodates all spatial acoustic effects belonging to the target position. SPEAR can be trained in a data much more readily accessible manner, in which we simply ask two robots to independently record spatial audio at different positions. We further theoretically prove the universal existence of the warping field if and only if one audio source presents. Three physical principles are incorporated to guide SPEAR network design, leading to the learned warping field physically meaningful. We demonstrate SPEAR superiority on both synthetic, photo-realistic and real-world dataset, showing the huge potential of SPEAR to various down-stream robotic tasks., Comment: 9 pages, 5 figures in main paper

Node classification on graphs is of great importance in many applications. Due to the limited labeling capability and evolution in real-world open scenarios, novel classes can emerge on unlabeled testing nodes. However, little attention has been paid to novel class discovery on graphs. Discovering novel classes is challenging as novel and known class nodes are correlated by edges, which makes their representations indistinguishable when applying message passing GNNs. Furthermore, the novel classes lack labeling information to guide the learning process. In this paper, we propose a novel method Open-world gRAph neuraL network (ORAL) to tackle these challenges. ORAL first detects correlations between classes through semi-supervised prototypical learning. Inter-class correlations are subsequently eliminated by the prototypical attention network, leading to distinctive representations for different classes. Furthermore, to fully explore multi-scale graph features for alleviating label deficiencies, ORAL generates pseudo-labels by aligning and ensembling label estimations from multiple stacked prototypical attention networks. Extensive experiments on several benchmark datasets show the effectiveness of our proposed method.

The phonon induced anomalous Hall or thermal Hall effects have been observed in various systems in recent experiments. However, the theoretical studies on this subject are very scarce and incomplete. In this work, we present a systematic quantum field theory study on the phonon induced anomalous Hall effect, including both the side jump and skew scattering contributions, in a 2D massive Dirac metal, which is considered as the minimum anomalous Hall system. We reveal significant difference from the anomalous Hall effect induced by the widely studied Gaussian disorder which is known to be insensitive to temperature. While the anomalous Hall effect induced by phonon approaches that by Gaussian disorder at high temperature, it behaves very differently at low temperature. Our work provides a microscopic and quantitative description of the crossover from the low to high temperature regime of the phonon induced anomalous Hall conductivity, which may be observed in 2D Dirac metals with breaking time reversal symmetry., Comment: Coherent skew scattering contribution added in the updated manuscript, accepted by PRB

Despite advancements in self-supervised monocular depth estimation, challenges persist in dynamic scenarios due to the dependence on assumptions about a static world. In this paper, we present MGDepth, a Motion-Guided Cost Volume Depth Net, to achieve precise depth estimation for both dynamic objects and static backgrounds, all while maintaining computational efficiency. To tackle the challenges posed by dynamic content, we incorporate optical flow and coarse monocular depth to create a novel static reference frame. This frame is then utilized to build a motion-guided cost volume in collaboration with the target frame. Additionally, to enhance the accuracy and resilience of the network structure, we introduce an attention-based depth net architecture to effectively integrate information from feature maps with varying resolutions. Compared to methods with similar computational costs, MGDepth achieves a significant reduction of approximately seven percent in root-mean-square error for self-supervised monocular depth estimation on the KITTI-2015 dataset.

The introduction of neural radiance fields has greatly improved the effectiveness of view synthesis for monocular videos. However, existing algorithms face difficulties when dealing with uncontrolled or lengthy scenarios, and require extensive training time specific to each new scenario. To tackle these limitations, we propose DynPoint, an algorithm designed to facilitate the rapid synthesis of novel views for unconstrained monocular videos. Rather than encoding the entirety of the scenario information into a latent representation, DynPoint concentrates on predicting the explicit 3D correspondence between neighboring frames to realize information aggregation. Specifically, this correspondence prediction is achieved through the estimation of consistent depth and scene flow information across frames. Subsequently, the acquired correspondence is utilized to aggregate information from multiple reference frames to a target frame, by constructing hierarchical neural point clouds. The resulting framework enables swift and accurate view synthesis for desired views of target frames. The experimental results obtained demonstrate the considerable acceleration of training time achieved - typically an order of magnitude - by our proposed method while yielding comparable outcomes compared to prior approaches. Furthermore, our method exhibits strong robustness in handling long-duration videos without learning a canonical representation of video content.

Few-shot learning (FSL) presents immense potential in enhancing model generalization and practicality for medical image classification with limited training data; however, it still faces the challenge of severe overfitting in classifier training due to distribution bias caused by the scarce training samples. To address the issue, we propose MedMFG, a flexible and lightweight plug-and-play method designed to generate sufficient class-distinctive features from limited samples. Specifically, MedMFG first re-represents the limited prototypes to assign higher weights for more important information features. Then, the prototypes are variationally generated into abundant effective features. Finally, the generated features and prototypes are together to train a more generalized classifier. Experiments demonstrate that MedMFG outperforms the previous state-of-the-art methods on cross-domain benchmarks involving the transition from natural images to medical images, as well as medical images with different lesions. Notably, our method achieves over 10% performance improvement compared to several baselines. Fusion experiments further validate the adaptability of MedMFG, as it seamlessly integrates into various backbones and baselines, consistently yielding improvements of over 2.9% across all results., Comment: 8 pages,5 figures, Accepted to BIBM2023

High-brilliance high-polarization $\gamma$ rays based on Compton scattering are of great significance in broad areas, such as nuclear, high-energy, astro-physics, etc. However, the transfer mechanism of spin angular momentum in the transition from linear, through weakly into strongly nonlinear processes is still unclear, which severely limits the simultaneous control of brilliance and polarization of high-energy $\gamma$ rays. In this work, we investigate the manipulation mechanism of high-quality polarized $\gamma$ rays in Compton scattering of the ultrarelativistic electron beam colliding with an intense laser pulse. We find that the contradiction lies in the simultaneous achievement of high-brilliance and high-polarization of $\gamma$ rays by increasing laser intensity, since the polarization is predominately contributed by the electron (laser photon) spin via multi-photon (single-photon) absorption channel. Moreover, we confirm that the signature of $\gamma$-ray polarization can be applied for observing the nonlinear effects (multi-photon absorption) of Compton scattering with moderate-intensity laser facilities.

A truly generalizable approach to rigid segmentation and motion estimation is fundamental to 3D understanding of articulated objects and moving scenes. In view of the closely intertwined relationship between segmentation and motion estimates, we present an SE(3) equivariant architecture and a training strategy to tackle this task in an unsupervised manner. Our architecture is composed of two interconnected, lightweight heads. These heads predict segmentation masks using point-level invariant features and estimate motion from SE(3) equivariant features, all without the need for category information. Our training strategy is unified and can be implemented online, which jointly optimizes the predicted segmentation and motion by leveraging the interrelationships among scene flow, segmentation mask, and rigid transformations. We conduct experiments on four datasets to demonstrate the superiority of our method. The results show that our method excels in both model performance and computational efficiency, with only 0.25M parameters and 0.92G FLOPs. To the best of our knowledge, this is the first work designed for category-agnostic part-level SE(3) equivariance in dynamic point clouds., Comment: To appear at NeurIPS 2023

Reconfigurable intelligent surface (RIS) is a revolutionary technology that can customize the wireless channel and improve the energy efficiency of next-generation cellular networks. This letter proposes an environment-aware codebook design by employing the statistical channel state information (CSI) for RIS-assisted multiple-input single-output (MISO) systems. Specifically, first of all, we generate multiple virtual channels offline by utilizing the location information and design an environment-aware reflection coefficient codebook. Thus, we only need to estimate the composite channel and optimize the active transmit beamforming for each reflection coefficient in the pre-designed codebook, while simplifying the reflection optimization substantially. Moreover, we analyze the theoretical performance of the proposed scheme. Finally, numerical results verify the performance benefits of the proposed scheme over the cascaded channel estimation and passive beamforming as well as the existing codebook scheme in the face of channel estimation errors, albeit its significantly reduced overhead and complexity., Comment: 5 pages, 4 figures

Gaussian quantum steering is a type of quantum correlation in which two entangled states exhibit asymmetry. We present an efficient theoretical scheme for controlling quantum steering and enhancing entanglement in a Laguerre-Gaussian (LG) rotating cavity optomechanical system with an optical parametric amplifier (OPA) driven by coherent light. The numerical simulation results show that manipulating system parameters such as parametric gain $\chi$, parametric phase $\theta$, and rotating mirror frequency, among others, significantly improves mirror-mirror and mirror-cavity entanglement. In addition to bipartite entanglement, we achieve mirror-cavity-mirror tripartite entanglement. Another intriguing discovery is the control of quantum steering, for which we obtained several results by investigating it for various system parameters. We show that the steering directivity is primarily determined by the frequency of two rotating mirrors. Furthermore, for two rotating mirrors, quantum steering is found to be asymmetric both one-way and two-way. As a result, we can assert that the current proposal may help in the understanding of non-local correlations and entanglement verification tasks., Comment: 9 pages , 8 figures

We study the anomalous Hall effect (AHE) in tilted Weyl metals with Gaussian disorder due to the crossed X and {\Psi} diagrams in this work. The importance of such diagrams to the AHE has been demonstrated recently in two dimensional (2D) massive Dirac model and Rashba ferromagnets. It has been shown that the inclusion of such diagrams dramatically changes the total AHE in such systems. In this work, we show that the contributions from the X and {\Psi} diagrams to the AHE in tilted Weyl metals are of the same order of the non-crossing diagram we studied in a previous work, but with opposite sign. The total contribution of the X and {\Psi} diagrams cancels the majority part of the contribution from the non-crossing diagram in tilted Weyl metals, similar to the 2D massive Dirac model. We also discuss the difference of the contributions from the crossed diagrams between 2D massive Dirac model and the tilted Weyl metals. At last, we discuss the experimental relevance of observing the AHE due to the X and {\Psi} diagrams in type-I Weyl metal such as Co3Sn2S2., Comment: accepted by PRB

The spectrum of laser-plasma-generated X-rays is very important as it can characterize electron dynamics and also be useful for applications, and nowadays with the forthcoming high-repetition-rate laser-plasma experiments, there is a raising demand for online diagnosis for the X-ray spectrum. In this paper, scintillators and silicon PIN diodes are used to build a wideband online filter stack spectrometer. The genetic algorithm is used to optimize the arrangements of the X-ray sensors and filters by minimizing the condition number of the response matrix, thus the unfolding error can be significantly decreased according to the numerical experiments. The detector responses are quantitatively calibrated by irradiating the scintillator and PIN diode using different nuclides and comparing the measured gamma-ray peaks. Finally, a 15-channel spectrometer prototype has been implemented. The X-ray detector, front-end electronics, and back-end electronics are integrated into the prototype, and the prototype can determine the spectrum with 1 kHz repetition rates.

A transfer reaction and cluster-decay experiment, $^{12}$C($^{16}$O,$^{24}$Mg$\rightarrow$$\alpha$+$^{20}$Ne)$\alpha$, was performed at a beam energy of 96 MeV. Both recoil and decay $\alpha$ particles were detected in coincidence, allowing us to deduce the energy-momentum of a $^{20}$Ne fragment. A number of resonant states of $^{24}$Mg were reconstructed up to an excitation energy of approximately 30 MeV. Owing to the experimentally achieved excellent resolutions of the $Q$-value and excitation-energy spectra, the relative decay widths for each resonant state in $^{24}$Mg to various final states of $^{20}$Ne were extracted, alone with the total decay width. The obtained results provide good testing ground for theoretical descriptions of the multiple clustering configurations in $^{24}$Mg.

Reconfigurable intelligent surface (RIS) has recently emerged as a promising technology enabling next-generation wireless networks. In this letter, we develop an improved index modulation (IM) scheme by utilizing RIS to convey information. Specifically, we study an RIS-aided multiple-input single-output (MISO) system, in which the information bits are conveyed by reflection patterns of RIS rather than the conventional amplitude-phase constellation. Furthermore, the K-means algorithm is employed to optimize the reflection constellation to improve the error performance. Also, we propose a generalized Gray coding method for mapping information bits to an appropriate reflection constellation and analytically evaluate the error performance of the proposed scheme by deriving a tight upper bound of the average bit error rate (BER). Finally, numerical results verify the accuracy of our theoretical analysis as well as the substantially improved BER performance of the proposed RIS-based IM transmission scheme., Comment: 5 pages, 3 figures, accepted by IEEE CL

We study the anomalous Hall effect (AHE) in tilted Weyl metals with weak Gaussian disorder under the Kubo-Streda formalism in this work. To separate the three different contributions, namely the intrinsic, side jump and skew scattering contribution, it is usually considered necessary to go to the eigenstate (chiral) basis of the Kubo-Streda formula. However, it is more straight-forward to compute the total Hall current in the spin basis. For the reason, we develop a systematic and transparent scheme to separate the three different contributions in the spin basis for relativistic systems by building a one-to-one correspondence between the Feynman diagrams of the different mechanisms in the chiral basis and the products of the symmetric and anti-symmetric part of the polarization operator in the spin basis. We obtain the three contributions of the AHE in tilted Weyl metals by this scheme and found that the side jump contribution exceeds both the intrinsic and skew scattering contribution for the low-energy effective Hamiltonian. We compared the anomalous Hall current obtained from our scheme with the results from the semi-classical Boltzmann equation approach under the relaxation time approximation and found that the results from the two approaches agree with each other in the leading order of the tilting velocity.

Scene flow is a powerful tool for capturing the motion field of 3D point clouds. However, it is difficult to directly apply flow-based models to dynamic point cloud classification since the unstructured points make it hard or even impossible to efficiently and effectively trace point-wise correspondences. To capture 3D motions without explicitly tracking correspondences, we propose a kinematics-inspired neural network (Kinet) by generalizing the kinematic concept of ST-surfaces to the feature space. By unrolling the normal solver of ST-surfaces in the feature space, Kinet implicitly encodes feature-level dynamics and gains advantages from the use of mature backbones for static point cloud processing. With only minor changes in network structures and low computing overhead, it is painless to jointly train and deploy our framework with a given static model. Experiments on NvGesture, SHREC'17, MSRAction-3D, and NTU-RGBD demonstrate its efficacy in performance, efficiency in both the number of parameters and computational complexity, as well as its versatility to various static backbones. Noticeably, Kinet achieves the accuracy of 93.27% on MSRAction-3D with only 3.20M parameters and 10.35G FLOPS., Comment: To appear at CVPR 2022 (Source Code: https://github.com/jx-zhong-for-academic-purpose/Kinet )