Searcharxiv⌕ Search

arXiv subjects

Yu Zhou

Publications and source records attributed to Yu Zhou.

At least 253 records · Page 14Linked to original sources
arXiv2024

Two geometric models for graded skew-gentle algebras

In Part 1, we classify (indecomposable) objects in the perfect derived category $\mathrm{per}Λ$ of a graded skew-gentle algebra $Λ$, generalizing technique/results of Burban-Drozd and Deng to the graded setting. We also use the usual punctured marked surface $\mathbf{S}^λ$ with grading (and a full formal arc system) to give a geometric model for this classification. In Part2, we introduce a new surface $\mathbf{S}^λ_*$ with binaries from $\mathbf{S}^λ$ by replacing each puncture $P$ by a boundary component $*_P$ (called a binary) with one marked point, and composing an equivalent relation $D_{*_P}^2=\mathrm{id}$, where $D_{*_p}$ is the Dehn twist along $*_P$. Certain indecomposable objects in $\mathrm{per}Λ$ can be also classified by graded unknotted arcs on $\mathbf{S}^λ_*$. Moreover, using this new geometric model, we show that the intersections between any two unknotted arcs provide a basis of the morphisms between the corresponding arc objects, i.e. formula $\mathrm{Int}=\mathrm{dim}\mathrm{Hom}$ holds.

math.RT↗
arXiv2024

TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model

Existing scene text spotters are designed to locate and transcribe texts from images. However, it is challenging for a spotter to achieve precise detection and recognition of scene texts simultaneously. Inspired by the glimpse-focus spotting pipeline of human beings and impressive performances of Pre-trained Language Models (PLMs) on visual tasks, we ask: 1) "Can machines spot texts without precise detection just like human beings?", and if yes, 2) "Is text block another alternative for scene text spotting other than word or character?" To this end, our proposed scene text spotter leverages advanced PLMs to enhance performance without fine-grained detection. Specifically, we first use a simple detector for block-level text detection to obtain rough positional information. Then, we finetune a PLM using a large-scale OCR dataset to achieve accurate recognition. Benefiting from the comprehensive language knowledge gained during the pre-training phase, the PLM-based recognition module effectively handles complex scenarios, including multi-line, reversed, occluded, and incomplete-detection texts. Taking advantage of the fine-tuned language model on scene recognition benchmarks and the paradigm of text block detection, extensive experiments demonstrate the superior performance of our scene text spotter across multiple public benchmarks. Additionally, we attempt to spot texts directly from an entire scene image to demonstrate the potential of PLMs, even Large Language Models (LLMs).

cs.CV↗
arXiv2024

The nonequilibrium evolution near the phase boundary

Using the single-spin flipping dynamics, we study the nonequilibrium evolution near the entire phase boundary of the 3D Ising model, and find that the average of relaxation time (RT) near the first-order phase transition line (1st-PTL) is significantly larger than that near the critical point (CP). As the system size increases, the average of RT near the 1st-PTL increases at a higher power compared to that near the CP. We further show that RT near the 1st-PTL is not only non-self-averaging, but actually self-diverging: relative variance of RT increases with system size. The presence of coexisting and metastable states results in a substantial increase in randomness near the 1st-PTL, and therefore makes the equilibrium more difficult to achieve.

cond-mat.stat-mech↗
arXiv2024

Tunable compact on-chip superconducting switch

We develop a compact four-port superconducting switch with a tunable operating frequency in the range of 4.8 GHz -- 7.3 GHz. Isolation between channel exceeds 20~dB over a bandwidth of several hundred megahertz, exceeding 40 dB at some frequencies. The footprint of the device is $80\times420~μ$m. The tunability requires only a global flux bias without either permanent magnets or micro-electromechanical structures. As the switch is superconducting, the heat dissipation during operation is negligible. The device can operate at up to -80~dBm, which is equal to $2.5\times 10^6$ photons at 6 GHz per microsecond. The device show a possibility to be operated as a beamsplitter with tunable splitting ratio.

quant-ph↗
arXiv2024

Exploiting Low-level Representations for Ultra-Fast Road Segmentation

Achieving real-time and accuracy on embedded platforms has always been the pursuit of road segmentation methods. To this end, they have proposed many lightweight networks. However, they ignore the fact that roads are "stuff" (background or environmental elements) rather than "things" (specific identifiable objects), which inspires us to explore the feasibility of representing roads with low-level instead of high-level features. Surprisingly, we find that the primary stage of mainstream network models is sufficient to represent most pixels of the road for segmentation. Motivated by this, we propose a Low-level Feature Dominated Road Segmentation network (LFD-RoadSeg). Specifically, LFD-RoadSeg employs a bilateral structure. The spatial detail branch is firstly designed to extract low-level feature representation for the road by the first stage of ResNet-18. To suppress texture-less regions mistaken as the road in the low-level feature, the context semantic branch is then designed to extract the context feature in a fast manner. To this end, in the second branch, we asymmetrically downsample the input image and design an aggregation module to achieve comparable receptive fields to the third stage of ResNet-18 but with less time consumption. Finally, to segment the road from the low-level feature, a selective fusion module is proposed to calculate pixel-wise attention between the low-level representation and context feature, and suppress the non-road low-level response by this attention. On KITTI-Road, LFD-RoadSeg achieves a maximum F1-measure (MaxF) of 95.21% and an average precision of 93.71%, while reaching 238 FPS on a single TITAN Xp and 54 FPS on a Jetson TX2, all with a compact model size of just 936k parameters. The source code is available at https://github.com/zhouhuan-hust/LFD-RoadSeg.

cs.CV↗
arXiv2024

Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing

Visual text, a pivotal element in both document and scene images, speaks volumes and attracts significant attention in the computer vision domain. Beyond visual text detection and recognition, the field of visual text processing has experienced a surge in research, driven by the advent of fundamental generative models. However, challenges persist due to the unique properties and features that distinguish text from general objects. Effectively leveraging these unique textual characteristics is crucial in visual text processing, as observed in our study. In this survey, we present a comprehensive, multi-perspective analysis of recent advancements in this field. Initially, we introduce a hierarchical taxonomy encompassing areas ranging from text image enhancement and restoration to text image manipulation, followed by different learning paradigms. Subsequently, we conduct an in-depth discussion of how specific textual features such as structure, stroke, semantics, style, and spatial context are seamlessly integrated into various tasks. Furthermore, we explore available public datasets and benchmark the reviewed methods on several widely-used datasets. Finally, we identify principal challenges and potential avenues for future research. Our aim is to establish this survey as a fundamental resource, fostering continued exploration and innovation in the dynamic area of visual text processing.

cs.CV↗
arXiv2024

MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images

This paper studies zero-shot anomaly classification (AC) and segmentation (AS) in industrial vision. We reveal that the abundant normal and abnormal cues implicit in unlabeled test images can be exploited for anomaly determination, which is ignored by prior methods. Our key observation is that for the industrial product images, the normal image patches could find a relatively large number of similar patches in other unlabeled images, while the abnormal ones only have a few similar patches. We leverage such a discriminative characteristic to design a novel zero-shot AC/AS method by Mutual Scoring (MuSc) of the unlabeled images, which does not need any training or prompts. Specifically, we perform Local Neighborhood Aggregation with Multiple Degrees (LNAMD) to obtain the patch features that are capable of representing anomalies in varying sizes. Then we propose the Mutual Scoring Mechanism (MSM) to leverage the unlabeled test images to assign the anomaly score to each other. Furthermore, we present an optimization approach named Re-scoring with Constrained Image-level Neighborhood (RsCIN) for image-level anomaly classification to suppress the false positives caused by noises in normal images. The superior performance on the challenging MVTec AD and VisA datasets demonstrates the effectiveness of our approach. Compared with the state-of-the-art zero-shot approaches, MuSc achieves a $\textbf{21.1%}$ PRO absolute gain (from 72.7% to 93.8%) on MVTec AD, a $\textbf{19.4%}$ pixel-AP gain and a $\textbf{14.7%}$ pixel-AUROC gain on VisA. In addition, our zero-shot approach outperforms most of the few-shot approaches and is comparable to some one-class methods. Code is available at https://github.com/xrli-U/MuSc.

cs.CV↗
arXiv2024

Toward Real Text Manipulation Detection: New Dataset and New Solution

With the surge in realistic text tampering, detecting fraudulent text in images has gained prominence for maintaining information security. However, the high costs associated with professional text manipulation and annotation limit the availability of real-world datasets, with most relying on synthetic tampering, which inadequately replicates real-world tampering attributes. To address this issue, we present the Real Text Manipulation (RTM) dataset, encompassing 14,250 text images, which include 5,986 manually and 5,258 automatically tampered images, created using a variety of techniques, alongside 3,006 unaltered text images for evaluating solution stability. Our evaluations indicate that existing methods falter in text forgery detection on the RTM dataset. We propose a robust baseline solution featuring a Consistency-aware Aggregation Hub and a Gated Cross Neighborhood-attention Fusion module for efficient multi-modal information fusion, supplemented by a Tampered-Authentic Contrastive Learning module during training, enriching feature representation distinction. This framework, extendable to other dual-stream architectures, demonstrated notable localization performance improvements of 7.33% and 6.38% on manual and overall manipulations, respectively. Our contributions aim to propel advancements in real-world text tampering detection. Code and dataset will be made available at https://github.com/DrLuo/RTM

cs.CV↗
arXiv2024

Deep learning based Image Compression for Microscopy Images: An Empirical Study

With the fast development of modern microscopes and bioimaging techniques, an unprecedentedly large amount of imaging data are being generated, stored, analyzed, and even shared through networks. The size of the data poses great challenges for current data infrastructure. One common way to reduce the data size is by image compression. This present study analyzes classic and deep learning based image compression methods, and their impact on deep learning based image processing models. Deep learning based label-free prediction models (i.e., predicting fluorescent images from bright field images) are used as an example application for comparison and analysis. Effective image compression methods could help reduce the data size significantly without losing necessary information, and therefore reduce the burden on data management infrastructure and permit fast transmission through the network for data sharing or cloud computing. To compress images in such a wanted way, multiple classical lossy image compression techniques are compared to several AI-based compression models provided by and trained with the CompressAI toolbox using python. These different compression techniques are compared in compression ratio, multiple image similarity measures and, most importantly, the prediction accuracy from label-free models on compressed images. We found that AI-based compression techniques largely outperform the classic ones and will minimally affect the downstream label-free task in 2D cases. In the end, we hope the present study could shed light on the potential of deep learning based image compression and the impact of image compression on downstream deep learning based image analysis models.

eess.IV↗
arXiv2024

Observation and manipulation of quantum interference in a superconducting Kerr parametric oscillator

Quantum tunneling is the phenomenon that makes superconducting circuits "quantum". Recently, there has been a renewed interest in using quantum tunneling in phase space of a Kerr parametric oscillator as a resource for quantum information processing. Here, we report a direct observation of quantum interference induced by such tunneling in a planar superconducting circuit through Wigner tomography. We experimentally elucidate all essential properties of this quantum interference, such as mapping from Fock states to cat states, a temporal oscillation due to the pump detuning, as well as its characteristic Rabi oscillations and Ramsey fringes. Finally, we perform gate operations as manipulations of the observed quantum interference. Our findings lay the groundwork for further studies on quantum properties of superconducting Kerr parametric oscillators and their use in quantum information technologies.

quant-ph↗
arXiv2024

Indoor Obstacle Discovery on Reflective Ground via Monocular Camera

Visual obstacle discovery is a key step towards autonomous navigation of indoor mobile robots. Successful solutions have many applications in multiple scenes. One of the exceptions is the reflective ground. In this case, the reflections on the floor resemble the true world, which confuses the obstacle discovery and leaves navigation unsuccessful. We argue that the key to this problem lies in obtaining discriminative features for reflections and obstacles. Note that obstacle and reflection can be separated by the ground plane in 3D space. With this observation, we firstly introduce a pre-calibration based ground detection scheme that uses robot motion to predict the ground plane. Due to the immunity of robot motion to reflection, this scheme avoids failed ground detection caused by reflection. Given the detected ground, we design a ground-pixel parallax to describe the location of a pixel relative to the ground. Based on this, a unified appearance-geometry feature representation is proposed to describe objects inside rectangular boxes. Eventually, based on segmenting by detection framework, an appearance-geometry fusion regressor is designed to utilize the proposed feature to discover the obstacles. It also prevents our model from concentrating too much on parts of obstacles instead of whole obstacles. For evaluation, we introduce a new dataset for Obstacle on Reflective Ground (ORG), which comprises 15 scenes with various ground reflections, a total of more than 200 image sequences and 3400 RGB images. The pixel-wise annotations of ground and obstacle provide a comparison to our method and other methods. By reducing the misdetection of the reflection, the proposed approach outperforms others. The source code and the dataset will be available at https://github.com/XuefengBUPT/IndoorObstacleDiscovery-RG.

cs.CV↗
arXiv2023

Masked and Permuted Implicit Context Learning for Scene Text Recognition

Scene Text Recognition (STR) is difficult because of the variations in text styles, shapes, and backgrounds. Though the integration of linguistic information enhances models' performance, existing methods based on either permuted language modeling (PLM) or masked language modeling (MLM) have their pitfalls. PLM's autoregressive decoding lacks foresight into subsequent characters, while MLM overlooks inter-character dependencies. Addressing these problems, we propose a masked and permuted implicit context learning network for STR, which unifies PLM and MLM within a single decoder, inheriting the advantages of both approaches. We utilize the training procedure of PLM, and to integrate MLM, we incorporate word length information into the decoding process and replace the undetermined characters with mask tokens. Besides, perturbation training is employed to train a more robust model against potential length prediction errors. Our empirical evaluations demonstrate the performance of our model. It not only achieves superior performance on the common benchmarks but also achieves a substantial improvement of $9.1\%$ on the more challenging Union14M-Benchmark.

cs.CV↗
arXiv2023

Geocoronal Solar Wind Charge Exchange Process Associated with the 2006-December-13 Coronal Mass Ejection Event

We report the discovery of a geocoronal solar wind charge exchange (SWCX) event corresponding to the well-known 2006 December 13th coronal mass ejection (CME) event. Strong evidence for the charge exchange origin of this transient diffuse emission is provided by prominent non-thermal emission lines at energies of $\rm O^{7+}$, $\rm Ne^{9+}$, $\rm Mg^{11+}$, $\rm Si^{12+}$, $\rm Si^{13+}$. Especially, a 0.53 keV emission line that most likely arises from the $\rm N^{5+}$ $1s^1 5p^1 \to 1s^2$ transition is detected. Previously, the forecastability of SWCX occurrence with proton flares has been disputed. In this particular event, we found that the SWCX signal coincided with the arrival of the magnetic cloud inside CME, triggered with a time delay after the proton flux fluctuation as the CME shock front passed through the Earth. Moreover, a spacecraft orbital modulation in SWCX light curve suggests that the emission arises close to the Earth. The line of sight was found to always pass through the northern magnetospheric cusp. The SWCX intensity was high when the line of sight passed the dusk side of the cusp, suggesting an azimuthal anisotropy in the flow of solar-wind ions inside the cusp. An axisymmetric SWCX emission model is found to underestimate the observed peak intensity by a factor of about 50. We suggest this discrepancy is related to the azimuthal anisotropy of the solar-wind flow in the cusp.

astro-ph.SR↗
arXiv2023

Hard Label Black Box Node Injection Attack on Graph Neural Networks

While graph neural networks have achieved state-of-the-art performances in many real-world tasks including graph classification and node classification, recent works have demonstrated they are also extremely vulnerable to adversarial attacks. Most previous works have focused on attacking node classification networks under impractical white-box scenarios. In this work, we will propose a non-targeted Hard Label Black Box Node Injection Attack on Graph Neural Networks, which to the best of our knowledge, is the first of its kind. Under this setting, more real world tasks can be studied because our attack assumes no prior knowledge about (1): the model architecture of the GNN we are attacking; (2): the model's gradients; (3): the output logits of the target GNN model. Our attack is based on an existing edge perturbation attack, from which we restrict the optimization process to formulate a node injection attack. In the work, we will evaluate the performance of the attack using three datasets, COIL-DEL, IMDB-BINARY, and NCI1.

cs.LG↗
arXiv2023

Assessing and Improving Syntactic Adversarial Robustness of Pre-trained Models for Code Translation

Context: Pre-trained models (PTMs) have demonstrated significant potential in automatic code translation. However, the vulnerability of these models in translation tasks, particularly in terms of syntax, has not been extensively investigated. Objective: To fill this gap, our study aims to propose a novel approach CoTR to assess and improve the syntactic adversarial robustness of PTMs in code translation. Method: CoTR consists of two components: CoTR-A and CoTR-D. CoTR-A generates adversarial examples by transforming programs, while CoTR-D proposes a semantic distance-based sampling data augmentation method and adversarial training method to improve the model's robustness and generalization capabilities. The Pass@1 metric is used by CoTR to assess the performance of PTMs, which is more suitable for code translation tasks and offers a more precise evaluation in real world scenarios. Results: The effectiveness of CoTR is evaluated through experiments on real world Java to Python datasets. The results demonstrate that CoTR-A can significantly reduce the performance of existing PTMs, while CoTR-D effectively improves the robustness of PTMs. Conclusion: Our study identifies the limitations of current PTMs, including large language models, in code translation tasks. It highlights the potential of CoTR as an effective solution to enhance the robustness of PTMs for code translation tasks.

cs.SE↗
arXiv2023

Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge

The ability to actively ground task instructions from an egocentric view is crucial for AI agents to accomplish tasks or assist humans virtually. One important step towards this goal is to localize and track key active objects that undergo major state change as a consequence of human actions/interactions to the environment without being told exactly what/where to ground (e.g., localizing and tracking the `sponge` in video from the instruction "Dip the `sponge` into the bucket."). While existing works approach this problem from a pure vision perspective, we investigate to which extent the textual modality (i.e., task instructions) and their interaction with visual modality can be beneficial. Specifically, we propose to improve phrase grounding models' ability on localizing the active objects by: (1) learning the role of `objects undergoing change` and extracting them accurately from the instructions, (2) leveraging pre- and post-conditions of the objects during actions, and (3) recognizing the objects more robustly with descriptional knowledge. We leverage large language models (LLMs) to extract the aforementioned action-object knowledge, and design a per-object aggregation masking technique to effectively perform joint inference on object phrases and symbolic knowledge. We evaluate our framework on Ego4D and Epic-Kitchens datasets. Extensive experiments demonstrate the effectiveness of our proposed framework, which leads to>54% improvements in all standard metrics on the TREK-150-OPE-Det localization + tracking task, >7% improvements in all standard metrics on the TREK-150-OPE tracking task, and >3% improvements in average precision (AP) on the Ego4D SCOD task.

cs.CV↗
arXiv2023

Advancing Transformer's Capabilities in Commonsense Reasoning

Recent advances in general purpose pre-trained language models have shown great potential in commonsense reasoning. However, current works still perform poorly on standard commonsense reasoning benchmarks including the Com2Sense Dataset. We argue that this is due to a disconnect with current cutting-edge machine learning methods. In this work, we aim to bridge the gap by introducing current ML-based methods to improve general purpose pre-trained language models in the task of commonsense reasoning. Specifically, we experiment with and systematically evaluate methods including knowledge transfer, model ensemble, and introducing an additional pairwise contrastive objective. Our best model outperforms the strongest previous works by ~15\% absolute gains in Pairwise Accuracy and ~8.7\% absolute gains in Standard Accuracy.

cs.CL↗