检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Liu, Haixiong Li, Zuoyong Wu, Jiawei Zeng, Kun Hu, Rong Zeng, Wei Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Data Science Minjiang University Fuzhou350121 China School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen University Guangdong Shenzhen518107 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China School of Physics and Mechanical and Electrical Engineering Longyan University Longyan364012 China

SSL(Semi-supervised learning) is widely used in machine learning, which leverages labeled and unlabeled data to improve model performance. SSL aims to optimize class mutual information, but noisy pseudo-labels introduce false class information due to the scarcity of labels. Therefore, these algorithms often need significant training time to refine pseudo-labels for performance improvement iteratively. To tackle this challenge, we propose a novel plug-and-play method named ASCL(Accelerating Semi-Supervised Learning via Contrastive Learning). This method combines contrastive learning with uncertainty-based selection for performance improvement and accelerates the convergence of SSL algorithms. Contrastive learning initially emphasizes the mutual information between samples as a means to decrease dependence on pseudo-labels. Subsequently, it gradually turns to maximizing the mutual information between classes, aligning with the objective of semi-supervised learning. Uncertainty-based selection provides a robust mechanism for acquiring pseudo-labels. The combination of the contrastive learning module and the uncertainty-based selection module forms a virtuous cycle to improve the performance of the proposed model. Extensive experiments demonstrate that ASCL outperforms state-of-the-art methods in terms of both convergence efficiency and performance. In the experimental scenario where only one label is assigned per class in the CIFAR-10 dataset, the application of ASCL to Pseudo-label, UDA (Unsupervised Data Augmentation for Consistency Training), and Fixmatch benefits substantial improvements in classification accuracy. Specifically, the results demonstrate notable improvements in respect of 16.32%, 6.9%, and 24.43% when compared to the original outcomes. Moreover, the required training time is reduced by almost 50%. © 2024, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Non-autoregressive machine translation with probabilistic context-free grammar 23

Non-autoregressive machine translation with probabilistic co...

引用

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

作者： Shangtong Gui Chenze Shao Zhengrui Ma Xishan Zhang Yunji Chen Yang Feng State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and Cambricon Technologies State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences

Non-autoregressive Transformer(NAT) significantly accelerates the inference of neural machine translation. However, conventional NAT models suffer from limited expression power and performance degradation compared to autoregressive (AT) models due to the assumption of conditional independence among target tokens. To address these limitations, we propose a novel approach called PCFG-NAT, which leverages a specially designed Probabilistic Context-Free Grammar (PCFG) to enhance the ability of NAT models to capture complex dependencies among output tokens. Experimental results on major machine translation benchmarks demonstrate that PCFG-NAT further narrows the gap in translation quality between NAT and AT models. Moreover, PCFG-NAT facilitates a deeper understanding of the generated sentences, addressing the lack of satisfactory explainability in neural machine translation. Code is publicly available at https://***/ictnlp/PCFG-NAT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decoupling Learning and Remembering: a Bilevel Memory Framework with Knowledge Projection for Task-Incremental Learning

Decoupling Learning and Remembering: a Bilevel Memory Framew...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wenju Sun Qingyong Li Jing Zhang Wen Wang Yangli-Ao Geng Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Frontiers Science Center for Smart High-speed Railway System Beijing Jiaotong University The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University

The dilemma between plasticity and stability arises as a common challenge for incremental learning. In contrast, the human memory system is able to remedy this dilemma owing to its multilevel memory structure, which motivates us to propose a Bilevel Memory system with Knowledge Projection (BMKP) for incremental learning. BMKP decouples the functions of learning and remembering via a bilevel-memory design: a working memory responsible for adaptively model learning, to ensure plasticity; a long-term memory in charge of enduringly storing the knowledge incorporated within the learned model, to guarantee stability. However, an emerging issue is how to extract the learned knowledge from the working memory and assimilate it into the long-term memory. To approach this issue, we reveal that the parameters learned by the working memory are actually residing in a redundant high-dimensional space, and the knowledge incorporated in the model can have a quite compact representation under a group of pattern basis shared by all incremental learning tasks. Therefore, we propose a knowledge projection process to adaptively maintain the shared basis, with which the loosely organized model knowledge of working memory is projected into the compact representation to be remembered in the long-term memory. We evaluate BMKP on CIFAR-10, CIFAR-100, and Tiny-ImageNet. The experimental results show that BMKP achieves state-of-the-art performance with lower memory usage 1 1 The code is available at https://***/SunWenJu123/BMKP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Object Detection Based on Generalized Features

Few-Shot Object Detection Based on Generalized Features

引用

Artificial Intelligence and intelligent information processing (AIIIP), International Conference on

作者： Qiuqin Chen Xiao Ke Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou China Key Laboratory of Spatial Data Mining & Information Sharing Ministry of Education Fuzhou Fuzhou China

Few-shot object detection aims to rapidly detect novel classes of objects using a minimal number of annotated instances. Compared to methods such as meta-learning, few-shot object detection based on transfer learning can achieve better performance. However, when training on base-class datasets, the model gradually improves its detection performance on base classes but does not enhance its generalization. A base-class model lacking generalization tends to result in lower detection performance for novel classes during fine-tuning. To address the aforementioned issues, this paper tackles the problem from two aspects: firstly, we introduce the Confusion-Dropblock Module (CDM) to perturb the model's features, thus enhancing feature generalization. Secondly, we incorporate Deformable Convolution Modules to mitigate the impact of object shapes and sizes on detection performance, thereby improving overall detection performance. Experimental results on the COCO dataset demonstrate the effectiveness of the proposed algorithm, outperforming the compared methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IF-Font: ideographic description sequence-following font generation 24

IF-Font: ideographic description sequence-following font gen...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Xinping Chen Xiao Ke Wenzhong Guo Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou China and Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China

ISBN: (纸本)9798331314385

Few-shot font generation (FFG) aims to learn the target style from a limited number of reference glyphs and generate the remaining glyphs in the target font. Previous works focus on disentangling the content and style features of glyphs, combining the content features of the source glyph with the style features of the reference glyph to generate new glyphs. However, the disentanglement is challenging due to the complexity of glyphs, often resulting in glyphs that are influenced by the style of the source glyph and prone to artifacts. We propose IF-Font, a novel paradigm which incorporates Ideographic Description Sequence (IDS) instead of the source glyph to control the semantics of generated glyphs. To achieve this, we quantize the reference glyphs into tokens, and model the token distribution of target glyphs using corresponding IDS and reference tokens. The proposed method excels in synthesizing glyphs with neat and correct strokes, and enables the creation of new glyphs based on provided IDS. Extensive experiments demonstrate that our method greatly outperforms state-of-the-art methods in both one-shot and few-shot settings, particularly when the target styles differ significantly from the training font styles. The code is available at https://***/Stareven233/IF-Font.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DASC-SPT: Towards Self-Supervised Panoramic Semantic Segmentation

DASC-SPT: Towards Self-Supervised Panoramic Semantic Segment...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Tianlong Tan Bin Chen Hongliang Cao Chenggang Yan Yike Ma Feng Dai Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences Beijing China Shandong University University of Chinese Academy of Sciences Beijing China Hangzhou Dianzi University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Self-Supervised Semantic Segmentation, aiming to leverage masses of unlabeled data for boosting semantic segmentation, has been rapidly emerging as an active task in recent years. However, existing self-supervised semantic segmentation approaches mainly focus on planar images, leaving multiple distorted objects encountered in panoramic images unexplored due to the formidable challenge of handling heterogeneous degrees of distortions across different locations. In this paper, we propose a novel Self-Supervised Panoramic Semantic Segmentation model, termed DASC-SPT, built upon the mainstream contrastive learning framework. Towards distortions in panoramic images, we present two structures to better learn from distorted features by applying planar images. For the input images of self-supervision, we design a Spherical Projection Transformation (SPT) strategy that involves randomly projecting planar images onto various locations of the sphere to introduce the distortions. For pixel-wise distorted features, we construct a Deformation-aware Sampling Consistency (DASC) framework to further utilize the shared content and discrepancies caused by different distortions of paired views, where the deformation-aware consistency can be quantified on pixel-wise features. Both of the two components facilitate the model to adapt to distortions and boost panoramic semantic segmentation. Extensive comprehensive experiments on three panoramic datasets demonstrate the effectiveness and superiority of DASC-SPT approach.

关键词： Training Deformable models Adaptation models Computer vision Semantic segmentation Computational modeling Crops Contrastive learning Distortion Boosting

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: boosting can achieve modality reconcilement 24

ReconBoost: boosting can achieve modality reconcilement

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Cong Hua Qianqian Xu Shilong Bao Zhiyong Yang Qingming Huang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Accurate interpolation for scattered data through hierarchical residual refinement 23

Accurate interpolation for scattered data through hierarchic...

引用

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

作者： Shizhe Ding Boyang Xia Dongbo Bu Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and University of Chinese Academy of Sciences Beijing China and Central China Institute for Artificial Intelligence Technologies Zhengzhou China

Accurate interpolation algorithms are highly desired in various theoretical and engineering scenarios. Unlike the traditional numerical algorithms that have exact zero-residual constraints on observed points, the neural network-based interpolation methods exhibit non-zero residuals at these points. These residuals, which provide observations of an underlying residual function, can guide predicting interpolation functions, but have not been exploited by the existing approaches. To fill this gap, we propose Hierarchical INTerpolation Network (HINT), which utilizes the residuals on observed points to guide target function estimation in a hierarchical fashion. HINT consists of several sequentially arranged lightweight interpolation blocks. The first interpolation block estimates the main component of the target function, while subsequent blocks predict the residual components using observed points residuals of the preceding blocks. The main component and residual components are accumulated to form the final interpolation results. Furthermore, under the assumption that finer residual prediction requires a more focused attention range on observed points, we utilize hierarchical local constraints in correlation modeling between observed and target points. Extensive experiments demonstrate that HINT outperforms existing interpolation algorithms significantly in terms of interpolation accuracy across a wide variety of datasets, which underscores its potential for practical scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two Heads Are Better Than One: Improving Fake News Video Detection by Correlating with Neighbors

arXiv

引用

arXiv 2023年

作者： Qi, Peng Zhao, Yuyang Shen, Yufeng Ji, Wei Cao, Juan Chua, Tat-Seng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China National University of Singapore Singapore

The prevalence of short video platforms has spawned a lot of fake news videos, which have stronger propagation ability than textual fake news. Thus, automatically detecting fake news videos has been an important countermeasure in practice. Previous works commonly verify each news video individually with multimodal information. Nevertheless, news videos from different perspectives regarding the same event are commonly posted together, which contain complementary or contradictory information and thus can be used to evaluate each other mutually. To this end, we introduce a new and practical paradigm, i.e., cross-sample fake news video detection, and propose a novel framework, Neighbor-Enhanced fakE news video Detection (NEED), which integrates the neighborhood relationship of new videos belonging to the same event. NEED can be readily combined with existing single-sample detectors and further enhance their performances with the proposed graph aggregation (GA) and debunking rectification (DR) modules. Specifically, given the feature representations obtained from single-sample detectors, GA aggregates the neighborhood information with the dynamic graph to enrich the features of independent samples. After that, DR explicitly leverages the relationship between debunking videos and fake news videos to refute the candidate videos via textual and visual consistency. Extensive experiments on the public benchmark demonstrate that NEED greatly improves the performance of both single-modal (up to 8.34% in accuracy) and multimodal (up to 4.97% in accuracy) base detectors. Codes are available in https://***/ICTMCG/NEED. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Glance and focus: memory prompting for multi-event video question answering 23

Glance and focus: memory prompting for multi-event video que...

引用

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

作者： Ziyi Bai Ruiping Wang Xilin Chen Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China and University of Chinese Academy of Sciences Beijing China

Video Question Answering (VideoQA) has emerged as a vital tool to evaluate agents' ability to understand human daily behaviors. Despite the recent success of large vision language models in many multi-modal tasks, complex situation reasoning over videos involving multiple human-object interaction events still remains challenging. In contrast, humans can easily tackle it by using a series of episode memories as anchors to quickly locate question-related key moments for reasoning. To mimic this effective reasoning strategy, we propose the Glance-Focus model. One simple way is to apply an action detection model to predict a set of actions as key memories. However, these actions within a closed set vocabulary are hard to generalize to various video domains. Instead of that, we train an Encoder-Decoder to generate a set of dynamic event memories at the glancing stage. Apart from using supervised bipartite matching to obtain the event memories, we further design an unsupervised memory generation method to get rid of dependence on event annotations. Next, at the focusing stage, these event memories act as a bridge to establish the correlation between the questions with high-level event concepts and low-level lengthy video content. Given the question, the model first focuses on the generated key event memory, then focuses on the most relevant moment for reasoning through our designed multi-level cross-attention mechanism. We conduct extensive experiments on four Multi-Event VideoQA benchmarks including STAR, EgoTaskQA, AGQA, and NExT-QA. Our proposed model achieves state-of-the-art results, surpassing current large models in various challenging reasoning tasks. The code and models are available at https://***/ByZ0e/Glance-Focus.

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：