PyTorchKR Papers

최신 논문

총 500편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2402.18116

Block and Detail: Scaffolding Sketch-to-Image Generation

We introduce a novel sketch-to-image tool that aligns with the iterative refinement process of artists. Our tool lets users sketch blocking strokes to coarsely represent the placement and form of objects and detail strokes to refine their shape and silhouettes. We develop a two-pass algorithm for generating high-fidelity images from such sketches at any point in the iterative process. In the first pass we use a ControlNet to generate an image that strictly follows all the strokes (blocking and detail) and in the second pass we add variation by renoising regions surrounding blocking strokes. We also present a dataset generation scheme that, when used to train a ControlNet architecture, allows regions that do not contain strokes to be interpreted as not-yet-specified regions rather than empty space. We show that this partial-sketch-aware ControlNet can generate coherent elements from partial sketches that only contain a small number of strokes. The high-fidelity images produced by our approach serve as scaffolds that can help the user adjust the shape and proportions of objects or add additional elements to the composition. We demonstrate the effectiveness of our approach with a variety of examples and evaluative comparisons. Quantitatively, evaluative user feedback indicates that novice viewers prefer the quality of images from our algorithm over a baseline Scribble ControlNet for 84% of the pairs and found our images had less distortion in 81% of the pairs.

arXiv:2402.18309

Enhancing Roadway Safety: LiDAR-based Tree Clearance Analysis

In the efforts for safer roads, ensuring adequate vertical clearance above roadways is of great importance. Frequently, trees or other vegetation is growing above the roads, blocking the sight of traffic signs and lights and posing danger to traffic participants. Accurately estimating this space from simple images proves challenging due to a lack of depth information. This is where LiDAR technology comes into play, a laser scanning sensor that reveals a three-dimensional perspective. Thus far, LiDAR point clouds at the street level have mainly been used for applications in the field of autonomous driving. These scans, however, also open up possibilities in urban management. In this paper, we present a new point cloud algorithm that can automatically detect those parts of the trees that grow over the street and need to be trimmed. Our system uses semantic segmentation to filter relevant points and downstream processing steps to create the required volume to be kept clear above the road. Challenges include obscured stretches of road, the noisy unstructured nature of LiDAR point clouds, and the assessment of the road shape. The identified points of non-compliant trees can be projected from the point cloud onto images, providing municipalities with a visual aid for dealing with such occurrences. By automating this process, municipalities can address potential road space constraints, enhancing safety for all. They may also save valuable time by carrying out the inspections more systematically. Our open-source code gives communities inspiration on how to automate the process themselves.

arXiv:2402.17414공식 코드 · Papers with Code

Neural Video Compression with Feature Modulation

The emerging conditional coding-based neural video codec (NVC) shows superiority over commonly-used residual coding-based codec and the latest NVC already claims to outperform the best traditional codec. However, there still exist critical problems blocking the practicality of NVC. In this paper, we propose a powerful conditional coding-based NVC that solves two critical problems via feature modulation. The first is how to support a wide quality range in a single model. Previous NVC with this capability only supports about 3.8 dB PSNR range on average. To tackle this limitation, we modulate the latent feature of the current frame via the learnable quantization scaler. During the training, we specially design the uniform quantization parameter sampling mechanism to improve the harmonization of encoding and quantization. This results in a better learning of the quantization scaler and helps our NVC support about 11.4 dB PSNR range. The second is how to make NVC still work under a long prediction chain. We expose that the previous SOTA NVC has an obvious quality degradation problem when using a large intra-period setting. To this end, we propose modulating the temporal feature with a periodically refreshing mechanism to boost the quality. %Besides solving the above two problems, we also design a single model that can support both RGB and YUV colorspaces. Notably, under single intra-frame setting, our codec can achieve 29.7\% bitrate saving over previous SOTA NVC with 16\% MACs reduction. Our codec serves as a notable landmark in the journey of NVC evolution. The codes are at https://github.com/microsoft/DCVC.

arXiv:2402.13741

Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction

The in-context learning (ICL) for relational triple extraction (RTE) has achieved promising performance, but still encounters two key challenges: (1) how to design effective prompts and (2) how to select proper demonstrations. Existing methods, however, fail to address these challenges appropriately. On the one hand, they usually recast RTE task to text-to-text prompting formats, which is unnatural and results in a mismatch between the output format at the pre-training time and the inference time for large language models (LLMs). On the other hand, they only utilize surface natural language features and lack consideration of triple semantics in sample selection. These issues are blocking improved performance in ICL for RTE, thus we aim to tackle prompt designing and sample selection challenges simultaneously. To this end, we devise a tabular prompting for RTE (\textsc{TableIE}) which frames RTE task into a table generation task to incorporate explicit structured information into ICL, facilitating conversion of outputs to RTE structures. Then we propose instructive in-context learning (I$^2$CL) which only selects and annotates a few samples considering internal triple semantics in massive unlabeled samples.

arXiv:2402.12682

Smart Mobility Digital Twin Based Automated Vehicle Navigation System: A Proof of Concept

Digital twins (DTs) have driven major advancements across various industrial domains over the past two decades. With the rapid advancements in autonomous driving and vehicle-to-everything (V2X) technologies, integrating DTs into vehicular platforms is anticipated to further revolutionize smart mobility systems. In this paper, a new smart mobility DT (SMDT) platform is proposed for the control of connected and automated vehicles (CAVs) over next-generation wireless networks. In particular, the proposed platform enables cloud services to leverage the abilities of DTs to promote the autonomous driving experience. To enhance traffic efficiency and road safety measures, a novel navigation system that exploits available DT information is designed. The SMDT platform and navigation system are implemented with state-of-the-art products, e.g., CAVs and roadside units (RSUs), and emerging technologies, e.g., cloud and cellular V2X (C-V2X). In addition, proof-of-concept (PoC) experiments are conducted to validate system performance. The performance of SMDT is evaluated from two standpoints: (i) the rewards of the proposed navigation system on traffic efficiency and safety and, (ii) the latency and reliability of the SMDT platform. Our experimental results using SUMO-based large-scale traffic simulations show that the proposed SMDT can reduce the average travel time and the blocking probability due to unexpected traffic incidents. Furthermore, the results record a peak overall latency for DT modeling and route planning services to be 155.15 ms and 810.59 ms, respectively, which validates that our proposed design aligns with the 3GPP requirements for emerging V2X use cases and fulfills the targets of the proposed design. Our demonstration video can be found at https://youtu.be/3waQwlaHQkk.

arXiv:2402.10883

Electronic Conductivity Measurements in Solid Electrolytes Using an Ion Blocking Microelectrode: Noise Rejection Based on a Median Filter

A method of electronic conductivity measurement is presented. It combines two well known methods of electrochemistry: cyclic voltammetry and chronoamperometry. This DC technique uses the Hebb/Wagner approach to block ionic conduction when steady state conditions are reached and allows electronic conduction of solid electrolytes to be determined. In order to get short diffusion times, a micro contact is used as an ion blocking electrode. However, as the electronic conduction in electrolytes is and should be very low, the current is also very low, typically some tens of nanoamps. Thus, the heating system inevitably generates noise problems that are solved using a median filter. Our system allows the determination of the conductivities without any preliminary smoothing or fitting of the curves. Some results with oxygen ion conductors are also give

arXiv:2402.10882공식 코드 · Papers with Code

Universal Prompt Optimizer for Safe Text-to-Image Generation

Text-to-Image (T2I) models have shown great performance in generating images based on textual prompts. However, these models are vulnerable to unsafe input to generate unsafe content like sexual, harassment and illegal-activity images. Existing studies based on image checker, model fine-tuning and embedding blocking are impractical in real-world applications. Hence, we propose the first universal prompt optimizer for safe T2I (POSI) generation in black-box scenario. We first construct a dataset consisting of toxic-clean prompt pairs by GPT-3.5 Turbo. To guide the optimizer to have the ability of converting toxic prompt to clean prompt while preserving semantic information, we design a novel reward function measuring toxicity and text alignment of generated images and train the optimizer through Proximal Policy Optimization. Experiments show that our approach can effectively reduce the likelihood of various T2I models in generating inappropriate images, with no significant impact on text alignment. It is also flexible to be combined with methods to achieve better performance. Our code is available at https://github.com/wu-zongyu/POSI.

arXiv:2402.09209

A general mechanism for enhancer-insulator pairing reveals heterogeneous dynamics in long-distant 3D gene regulation

Cells regulate fates and complex body plans using spatiotemporal signaling cascades that alter gene expression. Enhancers, short DNA sequences (50-150 base pairs), help coordinate these cascades by attracting regulatory proteins to enhance the transcription of distal genes by binding to promoters. In humans, there are hundreds of thousands of enhancers dispersed across the genome, which poses a challenging coordination task to prevent unintended gene activation. To mitigate this problem, the genome contains additional DNA elements, insulators, that block enhancer-promoter interactions. However, there is an open problem with how the insulation works, especially as enhancer-insulator pairs may be separated by millions of base pairs. Based on recent empirical data from Hi-C experiments, this paper proposes a new mechanism that challenges the common paradigm that rests on specific insulator-insulator interactions. Instead, this paper introduces a stochastic looping model where enhancers bind weakly to surrounding chromatin. After calibrating the model to experimental data, we use simulations to study the broad distribution of hitting times between an enhancer and a promoter when there are blocking insulators. In some cases, there is a large difference between average and most probable hitting times, making it difficult to assign a typical time scale, hinting at highly defocused regulation times. We also map our computational model onto a resetting problem that allows us to derive several analytical results. Besides offering new insights into enhancer-insulator interactions, our paper advances the understanding of gene regulatory networks and causal connections between genome folding and gene activation.

arXiv:2402.09152

Improved Regret for Bandit Convex Optimization with Delayed Feedback

We investigate bandit convex optimization (BCO) with delayed feedback, where only the loss value of the action is revealed under an arbitrary delay. Let $n,T,\bar{d}$ denote the dimensionality, time horizon, and average delay, respectively. Previous studies have achieved an $O(\sqrt{n}T^{3/4}+(n\bar{d})^{1/3}T^{2/3})$ regret bound for this problem, whose delay-independent part matches the regret of the classical non-delayed bandit gradient descent algorithm. However, there is a large gap between its delay-dependent part, i.e., $O((n\bar{d})^{1/3}T^{2/3})$, and an existing $\Omega(\sqrt{\bar{d}T})$ lower bound. In this paper, we illustrate that this gap can be filled in the worst case, where $\bar{d}$ is very close to the maximum delay $d$. Specifically, we first develop a novel algorithm, and prove that it enjoys a regret bound of $O(\sqrt{n}T^{3/4}+\sqrt{dT})$ in general. Compared with the previous result, our regret bound is better for $d=O((n\bar{d})^{2/3}T^{1/3})$, and the delay-dependent part is tight in the worst case. The primary idea is to decouple the joint effect of the delays and the bandit feedback on the regret by carefully incorporating the delayed bandit feedback with a blocking update mechanism. Furthermore, we show that the proposed algorithm can improve the regret bound to $O((nT)^{2/3}\log^{1/3}T+d\log T)$ for strongly convex functions. Finally, if the action sets are unconstrained, we demonstrate that it can be simply extended to achieve an $O(n\sqrt{T\log T}+d\log T)$ regret bound for strongly convex and smooth functions.

arXiv:2402.08674공식 코드 · Papers with Code

The dynamic interplay between in-context and in-weight learning in humans and neural networks

Human learning embodies a striking duality: sometimes, we appear capable of following logical, compositional rules and benefit from structured curricula (e.g., in formal education), while other times, we rely on an incremental approach or trial-and-error, learning better from curricula that are randomly interleaved. Influential psychological theories explain this seemingly disparate behavioral evidence by positing two qualitatively different learning systems -- one for rapid, rule-based inferences and another for slow, incremental adaptation. It remains unclear how to reconcile such theories with neural networks, which learn via incremental weight updates and are thus a natural model for the latter type of learning, but are not obviously compatible with the former. However, recent evidence suggests that metalearning neural networks and large language models are capable of "in-context learning" (ICL) -- the ability to flexibly grasp the structure of a new task from a few examples. Here, we show that the dynamic interplay between ICL and default in-weight learning (IWL) naturally captures a broad range of learning phenomena observed in humans, reproducing curriculum effects on category-learning and compositional tasks, and recapitulating a tradeoff between flexibility and retention. Our work shows how emergent ICL can equip neural networks with fundamentally different learning properties that can coexist with their native IWL, thus offering a novel perspective on dual-process theories and human cognitive flexibility.

arXiv:2402.07302

A Review of the GIC Blocker Placement Problem

Space weather poses a tremendous threat to power systems: geomagnetic disturbances could result in widespread disruptions and long-duration blackouts, including severe damage to system components. To mitigate their impacts, a handful of strategies exist, with the most promising being the deployment of transformer neutral blocking devices. The high cost of these devices, however, precludes their installation at all substations; this motivates the development of effective solutions for the cost-effective placement of such devices. While the current state-of-the-art in blocker placement methods is insufficient to be applied to real-sized power grids, ongoing research continues to increase the size of networks for which the placement problem remains tractable. Along these lines, the contributions of this paper are two fold: first, a comprehensive overview of the current state-of-the-art in blocker placement methods is provided; and second, a complete optimization formulation - implemented and benchmarked in an open-source software - for the blocker placement problem is presented.

arXiv:2402.06249

Anomaly Unveiled: Securing Image Classification against Adversarial Patch Attacks

Adversarial patch attacks pose a significant threat to the practical deployment of deep learning systems. However, existing research primarily focuses on image pre-processing defenses, which often result in reduced classification accuracy for clean images and fail to effectively counter physically feasible attacks. In this paper, we investigate the behavior of adversarial patches as anomalies within the distribution of image information and leverage this insight to develop a robust defense strategy. Our proposed defense mechanism utilizes a clustering-based technique called DBSCAN to isolate anomalous image segments, which is carried out by a three-stage pipeline consisting of Segmenting, Isolating, and Blocking phases to identify and mitigate adversarial noise. Upon identifying adversarial components, we neutralize them by replacing them with the mean pixel value, surpassing alternative replacement options. Our model-agnostic defense mechanism is evaluated across multiple models and datasets, demonstrating its effectiveness in countering various adversarial patch attacks in image classification tasks. Our proposed approach significantly improves accuracy, increasing from 38.8\% without the defense to 67.1\% with the defense against LaVAN and GoogleAp attacks, surpassing prominent state-of-the-art methods such as LGS (53.86\%) and Jujutsu (60\%)

arXiv:2402.04332

Proactive Blockage Prediction for UAV assisted Handover in Future Wireless Network

The future wireless communication applications demand seamless connectivity, higher throughput, and low latency, for which the millimeter-wave (mmWave) band is considered a potential technology. Nevertheless, line-of-sight (LoS) is often mandatory for mmWave band communication, and it renders these waves sensitive to sudden changes in the environment. Therefore, it is necessary to maintain the LoS link for a reliable connection. One such technique to maintain LoS is using proactive handover (HO). However, proactive HO is challenging, requiring continuous information about the surrounding wireless network to anticipate potential blockage. This paper presents a proactive blockage prediction mechanism where an unmanned aerial vehicle (UAV) is used as the base station for HO. The proposed scheme uses computer vision (CV) to obtain potential blocking objects, user speed, and location. To assess the effectiveness of the proposed scheme, the system is evaluated using a publicly available dataset for blockage prediction. The study integrates scenarios from Vision-based Wireless (ViWi) and UAV channel modeling, generating wireless data samples relevant to UAVs. The antenna modeling on the UAV end incorporates a polarization-matched scenario to optimize signal reception. The results demonstrate that UAV-assisted Handover not only ensures seamless connectivity but also enhances overall network performance by 20%. This research contributes to the advancement of proactive blockage mitigation strategies in wireless networks, showcasing the potential of UAVs as dynamic and adaptable base stations.

arXiv:2402.03600공식 코드 · Papers with Code

Understanding and Counteracting Feature-Level Bias in Click-Through Rate Prediction

Common click-through rate (CTR) prediction recommender models tend to exhibit feature-level bias, which leads to unfair recommendations among item groups and inaccurate recommendations for users. While existing methods address this issue by adjusting the learning of CTR models, such as through additional optimization objectives, they fail to consider how the bias is caused within these models. To address this research gap, our study performs a top-down analysis on representative CTR models. Through blocking different components of a trained CTR model one by one, we identify the key contribution of the linear component to feature-level bias. We conduct a theoretical analysis of the learning process for the weights in the linear component, revealing how group-wise properties of training data influence them. Our experimental and statistical analyses demonstrate a strong correlation between imbalanced positive sample ratios across item groups and feature-level bias. Based on this understanding, we propose a minimally invasive yet effective strategy to counteract feature-level bias in CTR models by removing the biased linear weights from trained models. Additionally, we present a linear weight adjusting strategy that requires fewer random exposure records than relevant debiasing methods. The superiority of our proposed strategies are validated through extensive experiments on three real-world datasets.

arXiv:2402.03814공식 코드 · Papers with Code

Masked Graph Autoencoder with Non-discrete Bandwidths

Masked graph autoencoders have emerged as a powerful graph self-supervised learning method that has yet to be fully explored. In this paper, we unveil that the existing discrete edge masking and binary link reconstruction strategies are insufficient to learn topologically informative representations, from the perspective of message propagation on graph neural networks. These limitations include blocking message flows, vulnerability to over-smoothness, and suboptimal neighborhood discriminability. Inspired by these understandings, we explore non-discrete edge masks, which are sampled from a continuous and dispersive probability distribution instead of the discrete Bernoulli distribution. These masks restrict the amount of output messages for each edge, referred to as "bandwidths". We propose a novel, informative, and effective topological masked graph autoencoder using bandwidth masking and a layer-wise bandwidth prediction objective. We demonstrate its powerful graph topological learning ability both theoretically and empirically. Our proposed framework outperforms representative baselines in both self-supervised link prediction (improving the discrete edge reconstructors by at most 20%) and node classification on numerous datasets, solely with a structure-learning pretext. Our implementation is available at https://github.com/Newiz430/Bandana.

arXiv:2402.00091

Nash Soft Actor-Critic LEO Satellite Handover Management Algorithm for Flying Vehicles

Compared with the terrestrial networks (TN), which can only support limited coverage areas, low-earth orbit (LEO) satellites can provide seamless global coverage and high survivability in case of emergencies. Nevertheless, the swift movement of the LEO satellites poses a challenge: frequent handovers are inevitable, compromising the quality of service (QoS) of users and leading to discontinuous connectivity. Moreover, considering LEO satellite connectivity for different flying vehicles (FVs) when coexisting with ground terminals, an efficient satellite handover decision control and mobility management strategy is required to reduce the number of handovers and allocate resources that align with different users' requirements. In this paper, a novel distributed satellite handover strategy based on Multi-Agent Reinforcement Learning (MARL) and game theory named Nash-SAC has been proposed to solve these problems. From the simulation results, the Nash-SAC-based handover strategy can effectively reduce the handovers by over 16 percent and the blocking rate by over 18 percent, outperforming local benchmarks such as traditional Q-learning. It also greatly improves the network utility used to quantify the performance of the whole system by up to 48 percent and caters to different users requirements, providing reliable and robust connectivity for both FVs and ground terminals.

arXiv:2401.18064

Neural Locality Sensitive Hashing for Entity Blocking

Locality-sensitive hashing (LSH) is a fundamental algorithmic technique widely employed in large-scale data processing applications, such as nearest-neighbor search, entity resolution, and clustering. However, its applicability in some real-world scenarios is limited due to the need for careful design of hashing functions that align with specific metrics. Existing LSH-based Entity Blocking solutions primarily rely on generic similarity metrics such as Jaccard similarity, whereas practical use cases often demand complex and customized similarity rules surpassing the capabilities of generic similarity metrics. Consequently, designing LSH functions for these customized similarity rules presents considerable challenges. In this research, we propose a neuralization approach to enhance locality-sensitive hashing by training deep neural networks to serve as hashing functions for complex metrics. We assess the effectiveness of this approach within the context of the entity resolution problem, which frequently involves the use of task-specific metrics in real-world applications. Specifically, we introduce NLSHBlock (Neural-LSH Block), a novel blocking methodology that leverages pre-trained language models, fine-tuned with a novel LSH-based loss function. Through extensive evaluations conducted on a diverse range of real-world datasets, we demonstrate the superiority of NLSHBlock over existing methods, exhibiting significant performance improvements. Furthermore, we showcase the efficacy of NLSHBlock in enhancing the performance of the entity matching phase, particularly within the semi-supervised setting.

arXiv:2401.12262

Machine learning-based network intrusion detection for big and imbalanced data using oversampling, stacking feature embedding and feature extraction

Cybersecurity has emerged as a critical global concern. Intrusion Detection Systems (IDS) play a critical role in protecting interconnected networks by detecting malicious actors and activities. Machine Learning (ML)-based behavior analysis within the IDS has considerable potential for detecting dynamic cyber threats, identifying abnormalities, and identifying malicious conduct within the network. However, as the number of data grows, dimension reduction becomes an increasingly difficult task when training ML models. Addressing this, our paper introduces a novel ML-based network intrusion detection model that uses Random Oversampling (RO) to address data imbalance and Stacking Feature Embedding based on clustering results, as well as Principal Component Analysis (PCA) for dimension reduction and is specifically designed for large and imbalanced datasets. This model's performance is carefully evaluated using three cutting-edge benchmark datasets: UNSW-NB15, CIC-IDS-2017, and CIC-IDS-2018. On the UNSW-NB15 dataset, our trials show that the RF and ET models achieve accuracy rates of 99.59% and 99.95%, respectively. Furthermore, using the CIC-IDS2017 dataset, DT, RF, and ET models reach 99.99% accuracy, while DT and RF models obtain 99.94% accuracy on CIC-IDS2018. These performance results continuously outperform the state-of-art, indicating significant progress in the field of network intrusion detection. This achievement demonstrates the efficacy of the suggested methodology, which can be used practically to accurately monitor and identify network traffic intrusions, thereby blocking possible threats.

arXiv:2401.11751공식 코드 · Papers with Code

Boosting Multi-view Stereo with Late Cost Aggregation

Pairwise matching cost aggregation is a crucial step for modern learning-based Multi-view Stereo (MVS). Prior works adopt an early aggregation scheme, which adds up pairwise costs into an intermediate cost. However, we analyze that this process can degrade informative pairwise matchings, thereby blocking the depth network from fully utilizing the original geometric matching cues. To address this challenge, we present a late aggregation approach that allows for aggregating pairwise costs throughout the network feed-forward process, achieving accurate estimations with only minor changes of the plain CasMVSNet. Instead of building an intermediate cost by weighted sum, late aggregation preserves all pairwise costs along a distinct view channel. This enables the succeeding depth network to fully utilize the crucial geometric cues without loss of cost fidelity. Grounded in the new aggregation scheme, we propose further techniques addressing view order dependence inside the preserved cost, handling flexible testing views, and improving the depth filtering process. Despite its technical simplicity, our method improves significantly upon the baseline cascade-based approach, achieving comparable results with state-of-the-art methods with favorable computation overhead.

arXiv:2401.10872

An Experimental Study of Decentralized Matching

We present an experimental study of decentralized two-sided matching markets with no transfers. Experimental participants are informed of everyone's preferences and can make arbitrary non-binding match offers that get finalized when a period of market inactivity has elapsed. Several insights emerge. First, stable outcomes are prevalent. Second, while centralized clearinghouses commonly aim at implementing extremal stable matchings, our decentralized markets most frequently culminate in the median stable matching. Third, preferences' cardinal representations impact the stable partners participants match with. Last, the dynamics underlying our results exhibit strategic sophistication, with agents successfully avoiding cycles of blocking pairs.