检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Yu-An Zhang, Ruqing Chen, Wei Guo, Jiafeng Fan, Yixing de Rijke, Maarten Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS University of Chinese Academy of Sciences Beijing China University of Amsterdam Amsterdam Netherlands

Neural ranking models (NRMs) and dense retrieval (DR) models have given rise to substantial improvements in overall retrieval performance. In addition to their effectiveness, and motivated by the proven lack of robustness of deep learning-based approaches in other areas, there is growing interest in the robustness of deep learning-based approaches to the core retrieval problem. Adversarial attack methods that have so far been developed mainly focus on attacking NRMs, with very little attention being paid to the robustness of DR models. In this paper, we introduce the adversarial retrieval attack (AREA) task. The AREA task is meant to trick DR models into retrieving a target document that is outside the initial set of candidate documents retrieved by the DR model in response to a query. We consider the decision-based black-box adversarial setting, which is realistic in real-world search engines. To address the AREA task, we first employ existing adversarial attack methods designed for NRMs. We find that the promising results that have previously been reported on attacking NRMs, do not generalize to DR models: these methods underperform a simple term spamming method. We attribute the observed lack of generalizability to the interaction-focused architecture of NRMs, which emphasizes fine-grained relevance matching. DR models follow a different representation-focused architecture that prioritizes coarse-grained representations. We propose to formalize attacks on DR models as a contrastive learning problem in a multi-view representation space. The core idea is to encourage the consistency between each view representation of the target document and its corresponding viewer via view-wise supervision signals. Experimental results demonstrate that the proposed method can significantly outperform existing attack strategies in misleading the DR model with small indiscernible text perturbations. Copyright © 2023, The Authors. All rights reserved.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Adfq-Vit: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers

SSRN

引用

SSRN 2024年

作者： Jiang, Yanfeng Sun, Ning Xie, Xueshuo Yang, Fei Li, Tao College of Computer Science Nankai University Tianjin China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China Zhejiang Lab Zhejiang Hangzhou China Haihe Lab of ITAI Tianjin China

Vision Transformers (ViTs) have exhibited exceptional performance across diverse computer vision tasks, while their substantial parameter size incurs significantly increased memory and computational demands, impeding effective inference on resource-constrained devices. Quantization has emerged as a promising solution to mitigate these challenges, yet existing methods still suffer from significant accuracy loss at low-bit. We attribute this issue to the distinctive distributions of post-LayerNorm and post-GELU activations within ViTs, rendering conventional hardware-friendly quantizers ineffective, particularly in low-bit scenarios. To address this issue, we propose a novel framework called Activation-Distribution-Friendly post-training Quantization for Vision Transformers, ADFQ-ViT. Concretely, we introduce the Per-Patch Outlier-aware Quantizer to tackle irregular outliers in post-LayerNorm activations. This quantizer refines the granularity of the uniform quantizer to a per-patch level while retaining a minimal subset of values exceeding a threshold at full-precision. To handle the non-uniform distributions of post-GELU activations between positive and negative regions, we design the Shift-Log2 Quantizer, which shifts all elements to the positive region and then applies log2 quantization. Moreover, we present the Attention-score enhanced Module-wise Optimization which adjusts the parameters of each quantizer by reconstructing errors to further mitigate quantization error. Extensive experiments demonstrate ADFQ-ViT provides significant improvements over various baselines in image classification, object detection, and instance segmentation tasks at 4-bit. Specifically, when quantizing the ViT-B model to 4-bit, we achieve a 10.23% improvement in Top-1 accuracy on the ImageNet dataset. © 2024, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Continual Learning for Generative Retrieval over Dynamic Corpora

arXiv

引用

arXiv 2023年

作者： Chen, Jiangui Zhang, Ruqing Guo, Jiafeng de Rijke, Maarten Chen, Wei Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS University Chinese Academy of Sciences Beijing China University of Amsterdam Amsterdam Netherlands

Generative retrieval (GR) directly predicts the identifiers of relevant documents (i.e., docids) based on a parametric model. It has achieved solid performance on many ad-hoc retrieval tasks. So far, these tasks have assumed a static document collection. In many practical scenarios, however, document collections are dynamic, where new documents are continuously added to the corpus. The ability to incrementally index new documents while preserving the ability to answer queries with both previously and newly indexed relevant documents is vital to applying GR models. In this paper, we address this practical continual learning problem for GR. We put forward a novel Continual-LEarner for generatiVE Retrieval (CLEVER) model and make two major contributions to continual learning for GR: (i) To encode new documents into docids with low computational cost, we present Incremental Product Quantization, which updates a partial quantization codebook according to two adaptive thresholds;and (ii) To memorize new documents for querying without forgetting previous knowledge, we propose a memory-augmented learning mechanism, to form meaningful connections between old and new documents. Empirical results demonstrate the effectiveness and efficiency of the proposed model. © 2023, CC BY.

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

Topic-oriented Adversarial Attacks against Black-box Neural Ranking Models

arXiv

引用

arXiv 2023年

作者： Liu, Yu-An Zhang, Ruqing Guo, Jiafeng de Rijke, Maarten Chen, Wei Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS University of Chinese Academy of Sciences Beijing China University of Amsterdam Amsterdam Netherlands

Neural ranking models (NRMs) have attracted considerable attention in information retrieval. Unfortunately, NRMs may inherit the adversarial vulnerabilities of general neural networks, which might be leveraged by black-hat search engine optimization practitioners. Recently, adversarial attacks against NRMs have been explored in the paired attack setting, generating an adversarial perturbation to a target document for a specific query. In this paper, we focus on a more general type of perturbation and introduce the topic-oriented adversarial ranking attack task against NRMs, which aims to find an imperceptible perturbation that can promote a target document in ranking for a group of queries with the same topic. We define both static and dynamic settings for the task and focus on decision-based black-box attacks. We propose a novel framework to improve topic-oriented attack performance based on a surrogate ranking model. The attack problem is formalized as a Markov decision process (MDP) and addressed using reinforcement learning. Specifically, a topic-oriented reward function guides the policy to find a successful adversarial example that can be promoted in rankings to as many queries as possible in a group. Experimental results demonstrate that the proposed framework can significantly outperform existing attack strategies, and we conclude by re-iterating that there exist potential risks for applying NRMs in the real world. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A feature extraction with pose-auxiliary method for Person Reidentification 2

A feature extraction with pose-auxiliary method for Person R...

引用

2nd International Conference on Advanced Algorithms and Signal Image Processing, AASIP 2022

作者： Ma, ZePing Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Sichuan Chengdu610054 China School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu610054 China

ISBN: (纸本)9781510660571

Person re-identification is widely considered as a sub problem of image retrieval. It is a technology that uses computer vision technology to determine whether there is a specific pedestrian in an image or video, given a monitored pedestrian image, the pedestrian image under the cross device is retrieved. Many researches have been made to study how to match one people from two picture, but how to locating proper body parts has become a problem which could lead to misalign and wrongly divided sample. To solve this problem, we introduce a pose-auxiliary network to extract the position feature of pedestrian. We use a post estimation network to estimate the person's body location, then we decide whether it's a body part or a static obstacle by using a separated trained classifier. Then we compare these features from two picture and calculate their loss. Meanwhile, we use a graph-matching strategy to compare two pedestrians pose structure, which is also used into jugging the match problem. By using a multi-verification strategy, our method has some improvement than some previous study using Market-1501 and DukeMTMC-Reid datasets, but still remains room for improvement. © 2022 SPIE.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

GLSNet: A Global Guided Local Feature Stepwise Aggregation network for polyp segmentation

引用

Biomedical Signal Processing and Control 2024年 87卷

作者： Pan, Xiaoying Ma, Chenyang Mu, Yaya Bi, Manrong Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi‘an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi‘an710121 China School of Computer Science & Technology Xi'an University of Post & Telecommunications Xi‘an710121 China

Accurate polyp segmentation is of great significance for the prevention and diagnosis of early colon cancer. Transformer-based image segmentation models have been proposed for polyp segmentation with good results, however, these methods do not sufficiently consider the negative impact of background noise in different levels of features, resulting in the loss of local details. To alleviate this problem, we propose a GLSNet (A Global Guided Local Feature Stepwise Aggregation network for polyp segmentation) network, including a spatial feature enhancement (SFE) module, a globally guided local feature enhancement (GLFE) module, and a feature stepwise aggregation (FSA) module. SFE can enhance the spatial feature representation of polyps to better capture the polyp information in the features. GLFE uses high-level features to filter noise in low-level features to capture polyp information hidden in shallow features;FSA fuses the semantic and positional information of polyps across scales to obtain the final segmentation results. Qualitative and quantitative experiments were conducted on 7 benchmark datasets, and the experimental results demonstrated that GLSNet outperforms other existing methods and has stronger generalization performance. In particular, we achieved a mean Dice of 92.9% on the large-scale Kvasir dataset, and mean Dice of 81.3% and 81.6% on CVC-ColonDB and ETIS, respectively, which are significantly higher than those of the competing methods. © 2023

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Multi-Granularity-Aware Aspect Learning Model for Multi-Aspect Dense Retrieval

arXiv

引用

arXiv 2023年

作者： Sun, Xiaojie Bi, Keping Guo, Jiafeng Yang, Sihui Zhang, Qishen Liu, Zhongyi Zhang, Guannan Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS University of Chinese Academy of Sciences Beijing China Ant Group Beijing China

Dense retrieval methods have been mostly focused on unstructured text and less attention has been drawn to structured data with various aspects, e.g., products with aspects such as category and brand. Recent work has proposed two approaches to incorporate the aspect information into item representations for effective retrieval by predicting the values associated with the item aspects. Despite their efficacy, they treat the values as isolated classes (e.g., "Smart Homes", "Home, Garden & Tools", and "Beauty & Health") and ignore their fine-grained semantic relation. Furthermore, they either enforce the learning of aspects into the CLS token, which could confuse it from its designated use for representing the entire content semantics, or learn extra aspect embeddings only with the value prediction objective, which could be insufficient especially when there are no annotated values for an item aspect. Aware of these limitations, we propose a MUlti-granulaRity-aware Aspect Learning model (MURAL) for multi-aspect dense retrieval. It leverages aspect information across various granularities to capture both coarse and fine-grained semantic relations between values. Moreover, MURAL incorporates separate aspect embeddings as input to transformer encoders so that the masked language model objective can assist implicit aspect learning even without aspect-value annotations. Extensive experiments on two real-world datasets of products and mini-programs show that MURAL outperforms state-of-the-art baselines significantly. Code will be available at the URL © 2023, CC BY.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Semantic-Enhanced Differentiable Search Index Inspired by Learning Strategies

arXiv

引用

arXiv 2023年

作者： Tang, Yubao Zhu, Zuowei Wang, Shuaiqiang Zhang, Ruqing Yin, Dawei Guo, Jiafeng Chen, Jiangui Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS University of Chinese Academy of Sciences Beijing China Baidu Inc Beijing China

Recently, a new paradigm called Differentiable Search Index (DSI) has been proposed for document retrieval, wherein a sequence-to-sequence model is learned to directly map queries to relevant document identifiers. The key idea behind DSI is to fully parameterize traditional "index-retrieve" pipelines within a single neural model, by encoding all documents in the corpus into the model parameters. In essence, DSI needs to resolve two major questions: (1) how to assign an identifier to each document, and (2) how to learn the associations between a document and its identifier. In this work, we propose a Semantic-Enhanced DSI model (SE-DSI) motivated by Learning Strategies in the area of Cognitive Psychology. Our approach advances original DSI in two ways: (1) For the document identifier, we take inspiration from Elaboration Strategies in human learning. Specifically, we assign each document an Elaborative Description based on the query generation technique, which is more meaningful than a string of integers in the original DSI;and (2) For the associations between a document and its identifier, we take inspiration from Rehearsal Strategies in human learning. Specifically, we select fine-grained semantic features from a document as Rehearsal Contents to improve document memorization. Both the offline and online experiments show improved retrieval performance over prevailing baselines. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Caching Strategy Based on Many-to-Many Matching Game in D2D networks

引用

Tsinghua science and technology 2021年第6期26卷 857-868页

作者： Kaihang Yu Zhonggui Ma Runyu Ni Tao Zhang School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China Key Lab of Information Network Security Ministry of Public SecurityShanghai 201204China

Wireless edge caching has been proposed to reduce data traffic congestion in backhaul links, and it is being envisioned as one of the key components of next-generation wireless networks. This paper focuses on the influences of different caching strategies in Device-to-Device(D2D) networks. We model the D2D User Equipments(DUEs) as the Gauss determinantal point process considering the repulsion between DUEs, as well as the caching replacement process as a many-to-many matching game. By analyzing existing caching placement strategies, a new caching strategy is proposed, which represents the preference list of DUEs as the ratio of content popularity to cached probability. There are two distinct features in the proposed caching strategy.(1) It can cache other contents besides high popularity contents.(2) It can improve the cache hit ratio and reduce the latency compared with three caching placement strategies: Least Recently Used(LRU), Equal Probability Random Cache(EPRC), and the Most Popular Content Cache(MPC). Meanwhile, we analyze the effect of caching on the system performance in terms of different content popularity factors and cache capacity. Simulation results show that our proposed caching strategy is superior to the three other comparison strategies and can significantly improve the cache hit ratio and reduce the latency.

关键词： caching strategy Device-to-Device(D2D)networks Gauss determinantal point process many-to-many matching game

来源：评论

学校读者我要写书评

暂无评论

Video Frame Interpolation via Direct Synthesis with the Event-based Reference

Video Frame Interpolation via Direct Synthesis with the Even...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yuhan Liu Yongjian Deng Hao Chen Zhen Yang College of Computer Science Beijing University of Technology Key Lab of Computer Network and Information Integration Southeast University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Video Frame Interpolation (VFI) has witnessed a surge in popularity due to its abundant downstream applications. Event-based VFI (E-VFI) has recently propelled the ad-vancement of VFI. Thanks to the high temporal resolution benefits, event cameras can bridge the informational void present between successive video frames. Most state-of-the-art E-VFI methodologies follow the conventional VFI paradigm, which pivots on motion estimation between consecutive frames to generate intermediate frames through a process of warping and refinement. However, this reliance engenders a heavy dependency on the quality and consis-tency of keyframes, rendering these methods susceptible to challenges in extreme real-world scenarios, such as missing moving objects and severe occlusion dilemmas. This study proposes a novel E-VFI framework that directly synthesize intermediate frames leveraging event-based reference, obviating the necessity for explicit motion estimation and substantially enhancing the capacity to handle motion occlusion. Given the sparse and inher-ently noisy nature of event data, we prioritize the relia-bility of the event-based reference, leading to the development of an innovative event-aware reconstruction strategy for accurate reference generation. Besides, we implement a bi-directional event-guided alignment from keyframes to the reference using the introduced E-PCD module. Finally, a transformer-based decoder is adopted for prediction re-finement. Comprehensive experimental evaluations on both synthetic and real-world datasets underscore the superiority of our approach and its potential to execute high-quality VFI tasks.

关键词： Interpolation Motion estimation Noise Propulsion Transformers Rendering (computer graphics) Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：