首页/论文/2012.03377

arXiv 2012.033772020-12-06cs.CVcs.AI

Art Style Classification with Self-Trained Ensemble of AutoEncoding Transformations

Universität des Saarlandes（萨尔兰大学）

Akshay Joshi, Ankit Agrawal, Sushmita Nair

备注：: 6

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

The artistic style of a painting is a rich descriptor that reveals both visual and deep intrinsic knowledge about how an artist uniquely portrays and expresses their creative vision. Accurate categorization of paintings across different artistic movements and styles is critical for large-scale indexing of art databases. However, the automatic extraction and recognition of these highly dense artistic features has received little to no attention in the field of computer vision research. In this paper, we investigate the use of deep self-supervised learning methods to solve the problem of recognizing complex artistic styles with high intra-class and low inter-class variation. Further, we outperform existing approaches by almost 20% on a highly class imbalanced WikiArt dataset with 27 art categories. To achieve this, we train the EnAET semi-supervised learning model (Wang et al., 2019) with limited annotated data samples and supplement it with self-supervised representations learned from an ensemble of spatial and non-spatial transformations.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Ensemble of Pre-Trained Neural Networks for Segmentation and Quality Detection of Transmission Electron Microscopy Images

Argonne National Laboratory（阿贡国家实验室）；Corning Inc.（康宁公司）

Automated analysis of electron microscopy datasets poses multiple challenges, such as limitation in the size of the training dataset, variation in data distribution induced by variation in sample quality and experiment conditions, etc. It is crucial for the trained model to continue to provide acceptable segmentation/classification performance on new data, and quantify the uncertainty associated with its predictions. Among the broad applications of machine learning, various approaches have been adopted to quantify uncertainty, such as Bayesian modeling, Monte Carlo dropout, ensembles, etc. Wit…

2022-09-05cond-mat.mtrl-scics.AIcs.CV

Exploring Content Based Image Retrieval for Highly Imbalanced Melanoma Data using Style Transfer, Semantic Image Segmentation and Ensemble Learning

Gujarat Technological University（古吉拉特理工大学）

Lesion images are frequently taken in open-set settings. Because of this, the image data generated is extremely varied in nature.It is difficult for a convolutional neural network to find proper features and generalise well, as a result content based image retrieval (CBIR) system for lesion images are difficult to build. This paper explores this domain and proposes multiple similarity measures which uses Style Loss and Dice Coefficient via a novel similarity measure called I1-Score. Out of the CBIR similarity measures proposed, pure style loss approach achieves a remarkable accuracy increase o…

2021-10-12cs.CV

深度集成艺术风格识别

Deep Ensemble Art Style Recognition

School of Electrical and Computer Eng.（电气与计算机工程学院）；National Technical University of Athens（雅典国立技术大学）

本文针对艺术风格识别，比较8种深度网络并提出堆叠集成方法，结合多模型特征与元分类器，在WikiArt上取得68.55%的最先进准确率。

2024-05-19cs.AIcs.CV

面向壁画残片风格分类的片段感知视觉Transformer

Fragment-Aware Vision Transformers for Fresco-Fragment Style Classification

Ca’ Foscari University of Venice（威尼斯大学）；Dundalk Institute of Technology（邓多克理工学院）；University of Milan（米兰大学）

提出片段感知ViT框架，通过前景掩码、修复正则化和分布级对比学习提升壁画残片风格分类，集成模型在CLEOPATRA上准确率达0.656。

2026-10-06cs.CVcs.LG

DPStyler：面向无源域泛化的动态PromptStyler

DPStyler: Dynamic PromptStyler for Source-Free Domain Generalization

Southeast University（东南大学）；National Center of Technology Innovation for EDA（国家EDA技术创新中心）

针对无源域泛化中风格模拟效率低及域不变信息提取难的问题，提出含风格生成与去除模块的DPStyler，结合模型集成缓解提示敏感性，在基准数据集上性能超越现有最优方法。

2024-07-14cs.CV

极端不平衡下的车辆分类：集成学习与 CNN 的比较研究

Vehicle Classification under Extreme Imbalance: A Comparative Study of Ensemble Learning and CNNs

Korea Advanced Institute of Science & Technology (KAIST)（韩国科学技术院）

针对车辆类别极端不平衡问题，论文构建 16 类约 4.7 万图像语料库，比较 SMOTE 再平衡的轻量级集成与增强训练的 ResNet 风格 CNN，证明 CNN 更优并指出少数类仍需数据与代价敏感方法。

2025-09-29cs.AIcs.CV

更多相关论文收起更多论文

Neural Style Transfer Improves 3D Cardiovascular MR Image Segmentation on Inconsistent Data

Department of Computer Science and Engineering, University at Buffalo, The State University of New York（纽约州立大学布法罗分校计算机科学与工程系）

Three-dimensional medical image segmentation is one of the most important problems in medical image analysis and plays a key role in downstream diagnosis and treatment. Recent years, deep neural networks have made groundbreaking success in medical image segmentation problem. However, due to the high variance in instrumental parameters, experimental protocols, and subject appearances, the generalization of deep learning models is often hindered by the inconsistency in medical images generated by different machines and hospitals. In this work, we present StyleSegor, an efficient and easy-to-use …

2019-09-20cs.CV

Hydra: an Ensemble of Convolutional Neural Networks for Geospatial Land Classification

Universidade Tecnológica Federal do Paraná (UTFPR)（巴拉那联邦科技大学）；Universidade Federal da Bahia (UFBA)（巴伊亚联邦大学）；University of South Florida (USF)（南佛罗里达大学）

We describe in this paper Hydra, an ensemble of convolutional neural networks (CNN) for geospatial land classification. The idea behind Hydra is to create an initial CNN that is coarsely optimized but provides a good starting pointing for further optimization, which will serve as the Hydra's body. Then, the obtained weights are fine-tuned multiple times with different augmentation techniques, crop styles, and classes weights to form an ensemble of CNNs that represent the Hydra's heads. By doing so, we prompt convergence to different endpoints, which is a desirable aspect for ensembles. With th…

2019-03-20cs.CV

Understanding Intra-Class Knowledge Inside CNN

MIT（麻省理工学院）

Convolutional Neural Network (CNN) has been successful in image recognition tasks, and recent works shed lights on how CNN separates different classes with the learned inter-class knowledge through visualization. In this work, we instead visualize the intra-class knowledge inside CNN to better understand how an object class is represented in the fully-connected layers. To invert the intra-class knowledge into more interpretable images, we propose a non-parametric patch prior upon previous CNN visualization models. With it, we show how different "styles" of templates for an object class are org…

2015-07-21cs.CV

ARTEMIS：使用多判别器GAN生成艺术

ARTEMIS: Using GANs with Multiple Discriminators to Generate Art

提出ARTEMIS方法，利用预训练VGG提取风格表示，训练自编码器解码器作为GAN生成器，配合多判别器与自注意力，生成超现实几何风格的抽象艺术。

2023-11-14cs.CV

超越模型设计：数据导向训练与自我集成用于高斯色图像去噪

Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising

Hefei University of Technology（合肥工业大学）；Hangzhou Dianzi University（杭州电子科技大学）；Jinan University（暨南大学）；South China Agricultural University（华南农业大学）；The University of Tokyo（东京大学）

本文提出解决NTIRE 2026图像去噪挑战的新方法，通过更强大的数据导向训练和更完整的测试时间能力释放，提升Restormer架构性能。在固定噪声水平σ=50下，通过扩大训练数据集和两阶段优化，使PSNR提升至30.762 dB，SSIM达0.861。

2026-04-27cs.CV

PulmoSight-XAI：用于多标签胸部X光分类的具有梯度提升元学习的可解释多视图注意力集成

PulmoSight-XAI: An Explainable Multi-View Attention Ensemble with Gradient Boosting Meta-Learning for Multi-Label Chest X-Ray Classification

Department of Biomedical Engineering Bangladesh University of Engineering and Technology (BUET)（孟加拉国工程技术大学（BUET）生物医学工程系）

针对胸部X光分类挑战，提出分层多视图集成框架。用五个卷积神经网络分别处理正侧位片，结合多尺度特征融合与注意力模块，采用混合损失函数优化模型，通过分层元学习策略提升性能，兼具准确性与可解释性。

2026-07-07cs.AIcs.CVcs.LG

EAML：基于集成自注意力互学习的文档图像分类网络

EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification

University of La Rochelle（拉罗谢尔大学）；AllRead Machine Learning Technologies（AllRead机器学习技术公司）

本文提出EAML网络，结合自注意力融合模块与互学习正则化，同时学习图像和文本特征，在文档图像分类基准上超越现有方法。

2023-05-11cs.CV

Listen, Denoise, Action!：基于扩散模型的音频驱动动作合成

Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models

KTH Royal Institute of Technology（KTH皇家理工学院）；Motorica AB

本文提出基于DiffWave架构和Conformers的扩散模型，用于合成与音频同步的复杂人类动作，通过无分类器引导控制风格强度，并推广引导过程实现扩散模型的专家乘积集成以支持风格插值。

2023-05-16cs.CVcs.GRcs.HC

Self-supervised Augmentation Consistency for Adapting Semantic Segmentation

TU Darmstadt（达姆施塔特工业大学）

We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate. In contrast to previous work, we abandon the use of computationally involved adversarial objectives, network ensembles and style transfer. Instead, we employ standard data augmentation techniques $-$ photometric noise, flipping and scaling $-$ and ensure consistency of the semantic predictions across these image transformations. We develop this principle in a lightweight self-supervised framework trained on co-evolving pseudo labels without the need for cumbersome extra training ro…

2021-04-30cs.CVcs.LG

Ensembling Off-the-shelf Models for GAN Training

Carnegie Mellon University（卡内基梅隆大学）；Adobe（奥多比）

The advent of large-scale training has produced a cornucopia of powerful visual recognition models. However, generative models, such as GANs, have traditionally been trained from scratch in an unsupervised manner. Can the collective "knowledge" from a large bank of pretrained vision models be leveraged to improve GAN training? If so, with so many models to choose from, which one(s) should be selected, and in what manner are they most effective? We find that pretrained computer vision models can significantly improve performance when used in an ensemble of discriminators. Notably, the particula…

2022-05-04cs.CVcs.GRcs.LG