arXiv subjects

Qiang Zhou

Publications and source records attributed to Qiang Zhou.

At least 91 records · Page 5Linked to original sources

arXiv2023

Discrete frequency-bin entanglement generation via cascaded second-order nonlinear processes in Sagnac interferometer

Discrete frequency-bin entanglement is an essential resource for applications in quantum information processing. In this Letter, we propose and demonstrate a scheme to generate discrete frequency-bin entanglement with a single piece of periodically poled lithium niobate waveguide in a modified Sagnac interferometer. Correlated two-photon states in both directions of the Sagnac interferometer are generated through cascaded second-order optical nonlinear processes. A relative phase difference between the two states is introduced by changing the polarization state of pump light, thus manipulating the two-photon state at the output of the Sagnac interferometer. The generated two-photon state is sent into a fiber polarization splitter, then a pure discrete frequency-bin entangled two-photon state is obtained by setting the pump light. The frequency entanglement property is measured by a spatial quantum beating with a visibility of $96.0 \pm 6.1\%$. The density matrix is further obtained with a fidelity of $98.0 \pm 3.0\%$ to the ideal state. Our demonstration provides a promising method for the generation of pure discrete frequency-bin entanglement at telecom band, which is desired in quantum photonics.

quant-ph↗

arXiv2023

MimCo: Masked Image Modeling Pre-training with Contrastive Teacher

Recent masked image modeling (MIM) has received much attention in self-supervised learning (SSL), which requires the target model to recover the masked part of the input image. Although MIM-based pre-training methods achieve new state-of-the-art performance when transferred to many downstream tasks, the visualizations show that the learned representations are less separable, especially compared to those based on contrastive learning pre-training. This inspires us to think whether the linear separability of MIM pre-trained representation can be further improved, thereby improving the pre-training performance. Since MIM and contrastive learning tend to utilize different data augmentations and training strategies, combining these two pretext tasks is not trivial. In this work, we propose a novel and flexible pre-training framework, named MimCo, which combines MIM and contrastive learning through two-stage pre-training. Specifically, MimCo takes a pre-trained contrastive learning model as the teacher model and is pre-trained with two types of learning targets: patch-level and image-level reconstruction losses. Extensive transfer experiments on downstream tasks demonstrate the superior performance of our MimCo pre-training framework. Taking ViT-S as an example, when using the pre-trained MoCov3-ViT-S as the teacher model, MimCo only needs 100 epochs of pre-training to achieve 82.53% top-1 finetuning accuracy on Imagenet-1K, which outperforms the state-of-the-art self-supervised learning counterparts.

cs.CV↗

arXiv2023

Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation

Modern incremental learning for semantic segmentation methods usually learn new categories based on dense annotations. Although achieve promising results, pixel-by-pixel labeling is costly and time-consuming. Weakly incremental learning for semantic segmentation (WILSS) is a novel and attractive task, which aims at learning to segment new classes from cheap and widely available image-level labels. Despite the comparable results, the image-level labels can not provide details to locate each segment, which limits the performance of WILSS. This inspires us to think how to improve and effectively utilize the supervision of new classes given image-level labels while avoiding forgetting old ones. In this work, we propose a novel and data-efficient framework for WILSS, named FMWISS. Specifically, we propose pre-training based co-segmentation to distill the knowledge of complementary foundation models for generating dense pseudo labels. We further optimize the noisy pseudo masks with a teacher-student architecture, where a plug-in teacher is optimized with a proposed dense contrastive loss. Moreover, we introduce memory-based copy-paste augmentation to improve the catastrophic forgetting problem of old classes. Extensive experiments on Pascal VOC and COCO datasets demonstrate the superior performance of our framework, e.g., FMWISS achieves 70.7% and 73.3% in the 15-5 VOC setting, outperforming the state-of-the-art method by 3.4% and 6.1%, respectively.

cs.CV↗

arXiv2023

DPF: Learning Dense Prediction Fields with Weak Supervision

Nowadays, many visual scene understanding problems are addressed by dense prediction networks. But pixel-wise dense annotations are very expensive (e.g., for scene parsing) or impossible (e.g., for intrinsic image decomposition), motivating us to leverage cheap point-level weak supervision. However, existing pointly-supervised methods still use the same architecture designed for full supervision. In stark contrast to them, we propose a new paradigm that makes predictions for point coordinate queries, as inspired by the recent success of implicit representations, like distance or radiance fields. As such, the method is named as dense prediction fields (DPFs). DPFs generate expressive intermediate features for continuous sub-pixel locations, thus allowing outputs of an arbitrary resolution. DPFs are naturally compatible with point-level supervision. We showcase the effectiveness of DPFs using two substantially different tasks: high-level semantic parsing and low-level intrinsic image decomposition. In these two cases, supervision comes in the form of single-point semantic category and two-point relative reflectance, respectively. As benchmarked by three large-scale public datasets PASCALContext, ADE20K and IIW, DPFs set new state-of-the-art performance on all of them with significant margins. Code can be accessed at https://github.com/cxx226/DPF.

cs.CV↗

arXiv2023

Hertz-rate metropolitan quantum teleportation

Quantum teleportation can transfer an unknown quantum state between distant quantum nodes, which holds great promise in enabling large-scale quantum networks. To advance the full potential of quantum teleportation, quantum states must be faithfully transferred at a high rate over long distance. Despite recent impressive advances, a high-rate quantum teleportation system across metropolitan fiber networks is extremely desired. Here, we demonstrate a quantum teleportation system which transfers quantum states carried by independent photons at a rate of 7.1$\pm$0.4 Hz over 64-km-long fiber channel. An average single-photon fidelity of $\geqslant$ 90.6$\pm$2.6% is achieved, which exceeds the maximum fidelity of 2/3 in classical regime. Our result marks an important milestone towards quantum networks and opens the door to exploring quantum entanglement based informatic applications for the future quantum internet.

quant-ph↗

arXiv2023

D2Q-DETR: Decoupling and Dynamic Queries for Oriented Object Detection with Transformers

Despite the promising results, existing oriented object detection methods usually involve heuristically designed rules, e.g., RRoI generation, rotated NMS. In this paper, we propose an end-to-end framework for oriented object detection, which simplifies the model pipeline and obtains superior performance. Our framework is based on DETR, with the box regression head replaced with a points prediction head. The learning of points is more flexible, and the distribution of points can reflect the angle and size of the target rotated box. We further propose to decouple the query features into classification and regression features, which significantly improves the model precision. Aerial images usually contain thousands of instances. To better balance model precision and efficiency, we propose a novel dynamic query design, which reduces the number of object queries in stacked decoder layers without sacrificing model performance. Finally, we rethink the label assignment strategy of existing DETR-like detectors and propose an effective label re-assignment strategy for improved performance. We name our method D2Q-DETR. Experiments on the largest and challenging DOTA-v1.0 and DOTA-v1.5 datasets show that D2Q-DETR outperforms existing NMS-based and NMS-free oriented object detection methods and achieves the new state-of-the-art.

cs.CV↗

arXiv2023

LMSeg: Language-guided Multi-dataset Segmentation

It's a meaningful and attractive topic to build a general and inclusive segmentation model that can recognize more categories in various scenarios. A straightforward way is to combine the existing fragmented segmentation datasets and train a multi-dataset network. However, there are two major issues with multi-dataset segmentation: (1) the inconsistent taxonomy demands manual reconciliation to construct a unified taxonomy; (2) the inflexible one-hot common taxonomy causes time-consuming model retraining and defective supervision of unlabeled categories. In this paper, we investigate the multi-dataset segmentation and propose a scalable Language-guided Multi-dataset Segmentation framework, dubbed LMSeg, which supports both semantic and panoptic segmentation. Specifically, we introduce a pre-trained text encoder to map the category names to a text embedding space as a unified taxonomy, instead of using inflexible one-hot label. The model dynamically aligns the segment queries with the category embeddings. Instead of relabeling each dataset with the unified taxonomy, a category-guided decoding module is designed to dynamically guide predictions to each datasets taxonomy. Furthermore, we adopt a dataset-aware augmentation strategy that assigns each dataset a specific image augmentation pipeline, which can suit the properties of images from different datasets. Extensive experiments demonstrate that our method achieves significant improvements on four semantic and three panoptic segmentation datasets, and the ablation study evaluates the effectiveness of each component.

cs.CV↗

arXiv2023

Quantum storage of 1650 modes of single photons at telecom wavelength

To advance the full potential of quantum networks one should be able to distribute quantum resources over long distances at appreciable rates. As a consequence, all components in the networks need to have large multimode capacity to manipulate photonic quantum states. Towards this end, a multimode photonic quantum memory, especially one operating at telecom wavelength, remains a key challenge. Here we demonstrate a spectro-temporally multiplexed quantum memory at 1532 nm. Multimode quantum storage of telecom-band heralded single photons is realized by employing the atomic frequency comb protocol in a 10-m-long cryogenically cooled erbium doped silica fibre. The multiplexing encompasses five spectral channels - each 10 GHz wide - and in each of these up to 330 temporal modes, resulting in the simultaneous storage of 1650 modes of single photons. Our demonstrations open doors for high-rate quantum networks, which are essential for future quantum internet.

quant-ph↗

arXiv2022

GAMMA Challenge:Glaucoma grAding from Multi-Modality imAges

Color fundus photography and Optical Coherence Tomography (OCT) are the two most cost-effective tools for glaucoma screening. Both two modalities of images have prominent biomarkers to indicate glaucoma suspected. Clinically, it is often recommended to take both of the screenings for a more accurate and reliable diagnosis. However, although numerous algorithms are proposed based on fundus images or OCT volumes in computer-aided diagnosis, there are still few methods leveraging both of the modalities for the glaucoma assessment. Inspired by the success of Retinal Fundus Glaucoma Challenge (REFUGE) we held previously, we set up the Glaucoma grAding from Multi-Modality imAges (GAMMA) Challenge to encourage the development of fundus \& OCT-based glaucoma grading. The primary task of the challenge is to grade glaucoma from both the 2D fundus images and 3D OCT scanning volumes. As part of GAMMA, we have publicly released a glaucoma annotated dataset with both 2D fundus color photography and 3D OCT volumes, which is the first multi-modality dataset for glaucoma grading. In addition, an evaluation framework is also established to evaluate the performance of the submitted methods. During the challenge, 1272 results were submitted, and finally, top-10 teams were selected to the final stage. We analysis their results and summarize their methods in the paper. Since all these teams submitted their source code in the challenge, a detailed ablation study is also conducted to verify the effectiveness of the particular modules proposed. We find many of the proposed techniques are practical for the clinical diagnosis of glaucoma. As the first in-depth study of fundus \& OCT multi-modality glaucoma grading, we believe the GAMMA Challenge will be an essential starting point for future research.

cs.CV↗

arXiv2022

Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotations

Point annotations are considerably more time-efficient than bounding box annotations. However, how to use cheap point annotations to boost the performance of semi-supervised object detection remains largely unsolved. In this work, we present Point-Teaching, a weakly semi-supervised object detection framework to fully exploit the point annotations. Specifically, we propose a Hungarian-based point matching method to generate pseudo labels for point annotated images. We further propose multiple instance learning (MIL) approaches at the level of images and points to supervise the object detector with point annotations. Finally, we propose a simple-yet-effective data augmentation, termed point-guided copy-paste, to reduce the impact of the unmatched points. Experiments demonstrate the effectiveness of our method on a few datasets and various data regimes.

cs.CV↗

arXiv2022

High-quality multi-wavelength quantum light sources on silicon nitride micro-ring chip

Multi-wavelength quantum light sources, especially at telecom band, are extremely desired in quantum information technology. Despite recent impressive advances, such a quantum light source with high quality remains challenging. Here we demonstrate a multi-wavelength quantum light source using a silicon nitride micro-ring with a free spectral range of 200 GHz. The generation of eight pairs of correlated photons is ensured in a wavelength range of 25.6 nm. With device optimization and noise-rejecting filters, our source enables the generation of heralded single-photons - at a rate of 62 kHz with $g^{(2)}_{h}(0)=0.014\pm0.001$, and the generation of energy-time entangled photons - with a visibility of $99.39\pm 0.45\%$ in the Franson interferometer. These results, at room temperature and telecom wavelength, in a CMOS compatible platform, represent an important step towards integrated quantum light devices for the quantum networks.

quant-ph↗

arXiv2022

Point RCNN: An Angle-Free Framework for Rotated Object Detection

Rotated object detection in aerial images is still challenging due to arbitrary orientations, large scale and aspect ratio variations, and extreme density of objects. Existing state-of-the-art rotated object detection methods mainly rely on angle-based detectors. However, angle regression can easily suffer from the long-standing boundary problem. To tackle this problem, we propose a purely angle-free framework for rotated object detection, called Point RCNN, which mainly consists of PointRPN and PointReg. In particular, PointRPN generates accurate rotated RoIs (RRoIs) by converting the learned representative points with a coarse-to-fine manner, which is motivated by RepPoints. Based on the learned RRoIs, PointReg performs corner points refinement for more accurate detection. In addition, aerial images are often severely unbalanced in categories, and existing methods almost ignore this issue. In this paper, we also experimentally verify that re-sampling the images of the rare categories will stabilize training and further improve the detection performance. Experiments demonstrate that our Point RCNN achieves the new state-of-the-art detection performance on commonly used aerial datasets, including DOTA-v1.0, DOTA-v1.5, and HRSC2016.

cs.CV↗

arXiv2022

Wavelength-division multiplexing communications using integrated soliton microcomb laser source

In this Letter, we investigate the feasibility and performance of wavelength division multiplexed (WDM) optical communications using an integrated dissipative Kerr soliton micro-comb as the multi-channel laser source. First, we confirm that soliton microcomb pumped directly by a DFB laser self-injection locked to the host micro-cavity has sufficiently low frequency and amplitude noises to encode advanced data formats. Second, perfect soliton crystals are exploited to boost the power level of each microcomb line, so that they can be directly used for data modulation excluding pre-amplification. Third, in a proof-of-concept experiment we demonstrate 7-channel 16-QAM data transmissions using an integrated perfect soliton microcomb as the laser carriers, excellent data receiving performances are obtained under various fiber link distances and amplifier configurations. Our study reveals that fully integrated Kerr soliton microcombs are viable and advantageous for optical data communications.

physics.optics↗

arXiv2022

UnrealNAS: Can We Search Neural Architectures with Unreal Data?

Neural architecture search (NAS) has shown great success in the automatic design of deep neural networks (DNNs). However, the best way to use data to search network architectures is still unclear and under exploration. Previous work has analyzed the necessity of having ground-truth labels in NAS and inspired broad interest. In this work, we take a further step to question whether real data is necessary for NAS to be effective. The answer to this question is important for applications with limited amount of accessible data, and can help people improve NAS by leveraging the extra flexibility of data generation. To explore if NAS needs real data, we construct three types of unreal datasets using: 1) randomly labeled real images; 2) generated images and labels; and 3) generated Gaussian noise with random labels. These datasets facilitate to analyze the generalization and expressivity of the searched architectures. We study the performance of architectures searched on these constructed datasets using popular differentiable NAS methods. Extensive experiments on CIFAR, ImageNet and CheXpert show that the searched architectures can achieve promising results compared with those derived from the conventional NAS pipeline with real labeled data, suggesting the feasibility of performing NAS with unreal data.

cs.CV↗

arXiv2022

Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar

We introduce NSEdit (neural-symbolic edit), a novel Transformer-based code repair method. Given only the source code that contains bugs, NSEdit predicts an editing sequence that can fix the bugs. The edit grammar is formulated as a regular language, and the Transformer uses it as a neural-symbolic scripting interface to generate editing programs. We modify the Transformer and add a pointer network to select the edit locations. An ensemble of rerankers are trained to re-rank the editing sequences generated by beam search. We fine-tune the rerankers on the validation set to reduce over-fitting. NSEdit is evaluated on various code repair datasets and achieved a new state-of-the-art accuracy ($24.04\%$) on the Tufano small dataset of the CodeXGLUE benchmark. NSEdit performs robustly when programs vary from packages to packages and when buggy programs are concrete. We conduct detailed analysis on our methods and demonstrate the effectiveness of each component.

cs.LG↗

arXiv2022

Calibrating quantum hydrodynamic model for noble metals in nanoplasmonics

Quantum hydrodynamic model (QHDM) has become a versatile and efficient tool for studying plasmonics at the nanoscopic length scale. Yet its application to noble metals has not been sufficiently justified, in particular for situations where the metallic structures interface with dielectric material and electrons spill over the interfaces. In a recent work, we developed a refined QHDM, where the near-field effects and static polarization of metal ion lattice, and the electron affinity and static permittivity of the dielectric are incorporated. Here we perform a careful calibration of the model parameters for the refined QHDM. The model parameters are determined by benchmarking with (time-dependent) density functional theory calculations for special cases of simple metal. The predictive power of the refined QHDM with calibrated model parameters is faithfully demonstrated by the calculations of the optical responses from gold nanomatryoshkas of different sizes. The refined QHDM approach allows the quasinormal mode analysis for revealing the intrinsic optical properties of the nanoscopic metallic structures. We expect the well-calibrated refined QHDM would provide the nanoplasmonics community with a useful tool.

physics.optics↗

arXiv2022

Optimized design of the lithium niobate for spectrally-pure-state generation at MIR wavelengths using metaheuristic algorithm

Quantum light sources in the mid-infrared (MIR) band play an important role in many applications, such as quantum sensing, quantum imaging, and quantum communication. However, there is still a lack of high-quality quantum light sources in the MIR band, such as the spectrally pure single-photon source. In this work, we present the generation of spectrally-pure state in an optimized poled lithium niobate crystal using a metaheuristic algorithm. In particular, we adopt the particle swarm optimization algorithm to optimize the duty cycle of the poling period of the lithium niobate crystal. With our approach, the spectral purity can be improved from 0.820 to 0.998 under the third group-velocity-matched condition, and the wavelength-tunable range is from 3.0 $μ$m to 4.0 $μ$m for the degenerate case and 3.0 $μ$m to 3.7 $μ$m for the nondegenerate case. Our work paves the way for developing quantum photonic technologies at the MIR wavelength band.

quant-ph↗

arXiv2022

Delving Deep into the Generalization of Vision Transformers under Distribution Shifts

Vision Transformers (ViTs) have achieved impressive performance on various vision tasks, yet their generalization under distribution shifts (DS) is rarely understood. In this work, we comprehensively study the out-of-distribution (OOD) generalization of ViTs. For systematic investigation, we first present a taxonomy of DS. We then perform extensive evaluations of ViT variants under different DS and compare their generalization with Convolutional Neural Network (CNN) models. Important observations are obtained: 1) ViTs learn weaker biases on backgrounds and textures, while they are equipped with stronger inductive biases towards shapes and structures, which is more consistent with human cognitive traits. Therefore, ViTs generalize better than CNNs under DS. With the same or less amount of parameters, ViTs are ahead of corresponding CNNs by more than 5% in top-1 accuracy under most types of DS. 2) As the model scale increases, ViTs strengthen these biases and thus gradually narrow the in-distribution and OOD performance gap. To further improve the generalization of ViTs, we design the Generalization-Enhanced ViTs (GE-ViTs) from the perspectives of adversarial learning, information theory, and self-supervised learning. By comprehensively investigating these GE-ViTs and comparing with their corresponding CNN models, we observe: 1) For the enhanced model, larger ViTs still benefit more for the OOD generalization. 2) GE-ViTs are more sensitive to the hyper-parameters than their corresponding CNN models. We design a smoother learning strategy to achieve a stable training process and obtain performance improvements on OOD data by 4% from vanilla ViTs. We hope our comprehensive study could shed light on the design of more generalizable learning architectures.

cs.CV↗