检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Jinglun Zhou, Xinyu Jiang, Kaixun Hong, Lingyi Guo, Pinxue Chen, Zhaoyu Ge, Weifeng Zhang, Wenqiang Shanghai Engineering Research Center of Ai & Robotics Academy for Engineering & Technology Fudan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Engineering Research Center of Ai & Robotics Ministry of Education Academy for Engineering & Technology Fudan University China

ISBN: (纸本)9798400706868

Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This enriched data representation improves performance across various tasks. Existing methods for out-of-distribution (OOD) detection, a critical area where AI models encounter unseen data in real-world scenarios, rely heavily on whole-image features. These image-level features can include irrelevant information that hinders the detection of OOD samples, ultimately limiting overall performance. In this paper, we propose TagOOD, a novel approach for OOD detection that leverages vision language representations to achieve label-free object feature decoupling from whole images. This decomposition enables a more focused analysis of object semantics, enhancing OOD detection performance. Subsequently, TagOOD trains a lightweight network on the extracted object features to learn representative class centers. These centers capture the central tendencies of IND object classes, minimizing the influence of irrelevant image features during OOD detection. Finally, our approach efficiently detects OOD samples by calculating distance-based metrics as OOD scores between learned centers and test samples. We conduct extensive experiments to evaluate TagOOD on several benchmark datasets and demonstrate its superior performance compared to existing OOD detection methods. This work presents a novel perspective for further exploration of multimodal information utilization in OOD detection, with potential applications across various tasks. Code is available at: https://***/Jarvisgivemeasuit/tagood. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

One Model for Two Tasks: Cooperatively Recognizing and Recovering Low-Resolution Scene Text Images by Iterative Mutual Guidance

arXiv

引用

arXiv 2024年

作者： Zhao, Minyi Wang, Yang Guan, Jihong Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Department of Computer Science and Technology Tongji University China

Scene text recognition (STR) from high-resolution (HR) images has been significantly successful, however text reading on low-resolution (LR) images is still challenging due to insufficient visual information. Therefore, recently many scene text image super-resolution (STISR) models have been proposed to generate super-resolution (SR) images for the LR ones, then STR is done on the SR images, which thus boosts recognition performance. Nevertheless, these methods have two major weaknesses. On the one hand, STISR approaches may generate imperfect or even erroneous SR images, which mislead the subsequent recognition of STR models. On the other hand, as the STISR and STR models are jointly optimized, to pursue high recognition accuracy, the fidelity of SR images may be spoiled. As a result, neither the recognition performance nor the fidelity of STISR models are desirable. Then, can we achieve both high recognition performance and good fidelity? To this end, in this paper we propose a novel method called IMAGE (the abbreviation of Iterative MutuAl GuidancE) to effectively recognize and recover LR scene text images simultaneously. Concretely, IMAGE consists of a specialized STR model for recognition and a tailored STISR model to recover LR images, which are optimized separately. And we develop an iterative mutual guidance mechanism, with which the STR model provides high-level semantic information as clue to the STISR model for better super-resolution, meanwhile the STISR model offers essential low-level pixel clue to the STR model for more accurate recognition. Extensive experiments on two LR datasets demonstrate the superiority of our method over the existing works on both recognition performance and super-resolution fidelity. © 2024, CC BY-NC-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Training-free diffusion model adaptation for variable-sized text-to-image synthesis 23

Training-free diffusion model adaptation for variable-sized ...

引用

Proceedings of the 37th International Conference on Neural information processing Systems

作者： Zhiyu Jin Xuli Shen Bin Li Xiangyang Xue Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University and UniDT Technology

Diffusion models (DMs) have recently gained attention with state-of-the-art performance in text-to-image synthesis. Abiding by the tradition in deep learning, DMs are trained and evaluated on the images with fixed sizes. However, users are demanding for various images with specific sizes and various aspect ratio. This paper focuses on adapting text-to-image diffusion models to handle such variety while maintaining visual fidelity. First we observe that, during the synthesis, lower resolution images suffer from incomplete object portrayal, while higher resolution images exhibit repetitively disordered presentation. Next, we establish a statistical relationship indicating that attention entropy changes with token quantity, suggesting that models aggregate spatial information in proportion to image resolution. The subsequent interpretation on our observations is that objects are incompletely depicted due to limited spatial information for low resolutions, while repetitively disorganized presentation arises from redundant spatial information for high resolutions. From this perspective, we propose a scaling factor to alleviate the change of attention entropy and mitigate the defective pattern observed. Extensive experimental results validate the efficacy of the proposed scaling factor, enabling models to achieve better visual effects, image quality, and text alignment. Notably, these improvements are achieved without additional training or fine-tuning techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Graph Classification with Even a Single key Subgraph Per Class

Weakly-Supervised Graph Classification with Even a Single Ke...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Lu Zhang Chenbo Zhang Jihong Guan Shuigeng Zhou Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Department of Computer Science & Technology Tongji University China

ISBN: (数字)9798331506681

ISBN: (纸本)9798331506698

Traditional graph classification requires large amounts of labeled data, which is expensive and time-consuming to acquire, especially in some special scenarios that domain knowledge is indispensable for labeling graphs. Observing that some key subgraphs can determine the properties of graphs (e.g. the toxicity of drug molecules depend on some toxic functional groups), in this paper we explore to classify graphs using unlabeled graphs plus a small number of key subgraphs for each class, which is called weakly-supervised graph classification. To this end, we develop the WeGraph method, where the graph classifier is trained with subgraph-based self-supervised learning and divergence- minimization based fine-tuning. Moreover, we design a key subgraph extraction algorithm to iteratively extract and update the key subgraphs, which makes the training process a closed loop. We conduct extensive experiments on different types of graph datasets to evaluate the effectiveness of WeGraph. Experimental results show that WeGraph can achieve high performance even when only one key subgraph is provided for each class.

关键词： Training Drugs Toxicology Social networking (online) Self-supervised learning Minimization Classification algorithms labeling Iterative methods Data mining

来源：评论

学校读者我要写书评

暂无评论

How to Train Your Neural Network for Molecular Structure Generation from Mass Spectra?

How to Train Your Neural Network for Molecular Structure Gen...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhao, Kai Liu, Yanmin Dian, Longyang Sun, Shiwei Cui, Xuefeng Shandong University School of Computer Science and Technology Qingdao China Shandong University State Key Laboratory of Microbial Technology Qingdao China Chinese Academy of Sciences Key Lab of Intelligent Information Processing Institute of Computing Technology Beijing China

ISBN: (纸本)9798350386226

Mass spectrometry serves as a pivotal tool for the analysis of small molecules through an examination of their mass-to-charge ratios. Recent advancements in deep learning have markedly enhanced the analysis of mass spectrometric data, facilitating the prediction of novel small molecule structures without the necessity of extensive databases. Nonetheless, the paucity of annotated datasets impedes the efficacious training of molecular generation models predicated on MS2 spectra. To mitigate this limitation, we introduce ctMSNovelist, an avant-garde method that amalgamates pre-training, fine-tuning, and co-training techniques to construct a more precise model for the generation of molecular structures from tandem mass spectrometry data. This novel approach augments both the training regimen and the predictive accuracy of the MSNovelist model, thereby surmounting the obstacle of limited data. The methodology commences with the pretraining of a Variational Autoencoder (VAE) to generate molecular fingerprints derived from SMILES strings. Subsequently, it undergoes fine-tuning to emulate noisy fingerprints originating from mass spectrometry (MS) data. Concurrently, MSNovelist is co-trained utilizing these simulated fingerprints, inclusive of the highly noisy variants produced in the early stages of VAE training. The incorporation of a substantial volume of noisy data serves to enhance model accuracy and avert overfitting. We evaluated ctMSNovelist using the GNPS dataset and attained a SMILES prediction accuracy of 48.8%, representing a 4.1% enhancement over MSNovelist. It is pertinent to note that the sole distinction between ctMSNovelist and MSNovelist in this experiment was the training process. The code and models are publicly available at https://***/xfcui/ctMSNovelist. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

HPPNET: MODELING THE HARMONIC STRUCTURE AND PITCH INVARIANCE IN PIANO TRANSCRIPTION 23

HPPNET: MODELING THE HARMONIC STRUCTURE AND PITCH INVARIANCE...

引用

23rd International Society for Music information Retrieval Conference, ISMIR 2022

作者： Wei, Weixing Li, Peilin Yu, Yi Li, Wei School of Computer Science and Technology Fudan University China Japan Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

ISBN: (纸本)9781732729926

While neural network models are making significant progress in piano transcription, they are becoming more resource-consuming due to requiring larger model size and more computing power. In this paper, we attempt to apply more prior about piano to reduce model size and improve the transcription performance. The sound of a piano note contains various overtones, and the pitch of a key does not change over time. To make full use of such latent information, we propose HPPNet that using the Harmonic Dilated Convolution to capture the harmonic structures and the Frequency Grouped Recurrent Neural Network to model the pitch-invariance over time. Experimental results on the MAESTRO dataset show that our piano transcription system achieves state-of-the-art performance both in frame and note scores (frame F1 93.15%, note F1 97.18%). Moreover, the model size is much smaller than the previous state-of-the-art deep learning models. © Weixing Wei, Peilin Li, Yi Yu, and Wei Li.

关键词： Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

AUITestAgent: Automatic Requirements Oriented GUI Function Testing

arXiv

引用

arXiv 2024年

作者： Hu, Yongxiang Wang, Xuan Wang, Yingchuan Zhang, Yu Guo, Shiyu Chen, Chaoyi Wang, Xin Zhou, Yangfan Meituan Shanghai China School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

The Graphical User Interface (GUI) is how users interact with mobile apps. To ensure it functions properly, testing engineers have to make sure it functions as intended, based on test requirements that are typically written in natural language. While widely adopted manual testing and script-based methods are effective, they demand substantial effort due to the vast number of GUI pages and rapid iterations in modern mobile apps. This paper introduces AUITestAgent, the first automatic, natural language-driven GUI testing tool for mobile apps, capable of fully automating the entire process of GUI interaction and function verification. Since test requirements typically contain interaction commands and verification oracles. AUITestAgent can extract GUI interactions from test requirements via dynamically organized agents. Then, AUITestAgent employs a multi-dimensional data extraction strategy to retrieve data relevant to the test requirements from the interaction trace and perform verification. Experiments on customized benchmarks 1 demonstrate that AUITestAgent outperforms existing tools in the quality of generated GUI interactions and achieved the accuracy of verifications of 94%. Moreover, field deployment in Meituan has shown AUITestAgent’s practical usability, with it detecting 4 new functional bugs during 10 regression tests in two months. Copyright © 2024, The Authors. All rights reserved.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Improving Transferability Reversible Adversarial Examples Based on Flipping Transformation 9th

Improving Transferability Reversible Adversarial Examples Ba...

引用

9th International Conference of Pioneering computer Scientists, Engineers and Educators, ICPCSEE 2023

作者： Fang, Youqing Jia, Jingwen Yang, Yuhai Lyu, Wanli Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China

ISBN: (纸本)9789819959679

Adding subtle perturbations to an image can cause the classification model to misclassify, and such images are called adversarial examples. Adversarial examples threaten the safe use of deep neural networks, but when combined with reversible data hiding (RDH) technology, they can protect images from being correctly identified by unauthorized models and recover the image lossless under authorized models. Based on this, the reversible adversarial example (RAE) is rising. However, existing RAE technology focuses on feasibility, attack success rate and image quality, but ignores transferability and time complexity. In this paper, we optimize the data hiding structure and combine data augmentation technology, which flips the input image in probability to avoid overfitting phenomenon on the dataset. On the premise of maintaining a high success rate of white-box attacks and the image’s visual quality, the proposed method improves the transferability of reversible adversarial examples by approximately 16% and reduces the computational cost by approximately 43% compared to the state-of-the-art method. In addition, the appropriate flip probability can be selected for different application scenarios. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Weight Perturbation as Defense against Adversarial Word Substitutions

Weight Perturbation as Defense against Adversarial Word Subs...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Xu, Jianhan Li, Linyang Zhang, Jiping Zheng, Xiaoqing Chang, Kai-Wei Hsieh, Cho-Jui Huang, Xuanjing School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing China Department of Computer Science University of California Los Angeles United States

The existence and pervasiveness of textual adversarial examples have raised serious concerns to security-critical applications. Many methods have been developed to defend against adversarial attacks for neural natural language processing (NLP) models. Adversarial training is one of the most successful defense methods by adding some random or intentional perturbations to the original input texts and making the models robust to the perturbed examples. In this study, we explore the feasibility of improving the adversarial robustness of NLP models by performing perturbations in the parameter space rather than the input feature space. The weight perturbation helps to find a better solution (i.e., the values of weights) that minimizes the adversarial loss among other feasible solutions. We found that the weight perturbation can significantly improve the robustness of NLP models when it is combined with the perturbation in the input embedding space, yielding the highest accuracy on both clean and adversarial examples across different datasets. © 2022 Association for Computational Linguistics.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

DCSN: A Flexible and Efficient Lightweight Network for Dense Cell Segmentation

DCSN: A Flexible and Efficient Lightweight Network for Dense...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Futai Pan Fei Wang Shanghai Key Lab of Intelligent Information Processing School of Computer Science and Technology Fudan University Shanghai China

Cells serve as the fundamental building blocks of living organisms and necessitate the utilization of diverse microscopic imaging techniques for observation. Nevertheless, there exist numerous limitations within phase-contrast microscopy imaging technology, leading to indistinct imaging in a considerable number of acquired cell images. Furthermore, the wide range of cell shapes and sizes, often densely distributed, poses challenges for research in the field of cell image analysis. We propose Dense Cell Segmentation Network (DCSN), an anchor-based single-stage instance segmentation method, to address the challenge of dense detection and instance segmentation in high-density cell images. While methods based on transformers have emerged as prominent approaches in natural image detection and segmentation, they are limited in their applicability to cell image analysis due to the scarcity of cell image datasets. Consequently, we aim to introduce a simple yet effective instance segmentation method to further address the challenge of cell image segmentation. DCSN is a lightweight multi-task model, combining object detection and semantic segmentation to achieve accurate instance segmentation. We validate our approach on LIVECell, a publicly available annotated cell dataset, and demonstrate its efficacy. By combining the advantages of anchor-based methods and single-stage methods, DCSN achieves a favorable balance between speed and performance. In comparison to the anchor-based two-stage model Mask R-CNN, DCSN offers a streamlined process and faster inference speed. Compared to the anchor-free single-stage method, CenterMask, our model demonstrates superior segmentation performance and generalization capabilities. Moreover,DCSN is a general end-to-end model that can be applied to various domains beyond cell segmentation tasks.

关键词：

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：