Learning image classification and image generation using the same set of network parameters is a challenging problem. Recent advanced approaches perform well in one task often exhibit poor performance in the other. This work introduces an energy-based classifier and generator, namely EGC, which can achieve superior performance in both tasks using a single neural network. Unlike a conventional classifier that outputs a label given an image (i.e., a conditional distribution $p(y|\mathbf{x})$), the forward pass in EGC is a classifier that outputs a joint distribution $p(\mathbf{x},y)$, enabling an image generator in its backward pass by marginalizing out the label $y$. This is done by estimating the energy and classification probability given a noisy image in the forward pass, while denoising it using the score function estimated in the backward pass. EGC achieves competitive generation results compared with state-of-the-art approaches on ImageNet-1k, CelebA-HQ and LSUN Church, while achieving superior classification accuracy and robustness against adversarial attacks on CIFAR-10. This work represents the first successful attempt to simultaneously excel in both tasks using a single set of network parameters. We believe that EGC bridges the gap between discriminative and generative learning.
Universidade Estadual de Maringá (UEM)（马林加州立大学）；Universidade Federal do Paraná (UFPR)（巴拉那联邦大学）；Instituto Federal do Paraná (IFPR)（巴拉那联邦理工学院）
Studies recently accomplished on the Enteric Nervous System have shown that chronic degenerative diseases affect the Enteric Glial Cells (EGC) and, thus, the development of recognition methods able to identify whether or not the EGC are affected by these type of diseases may be helpful in its diagnoses. In this work, we propose the use of pattern recognition and machine learning techniques to evaluate if a given animal EGC image was obtained from a healthy individual or one affect by a chronic degenerative disease. In the proposed approach, we have performed the classification task with handcr…
DiffSpectralNet : Unveiling the Potential of Diffusion Models for Hyperspectral Image Classification
University of Buckingham（白金汉大学）；University of Greenwich（格林威治大学）；Middlesex University（密德萨斯大学）；International University–Vietnam National University of HCMC（胡志明市越南国家大学国际大学）
Self-learned representation-guided latent diffusion model for breast cancer classification in deep ultraviolet whole surface images
Department of Computer Science, Georgia State University（计算机科学系，佐治亚州立大学）；Department of Electrical and Computer Engineering, Marquette University（电气与计算机工程系，马基特大学）；Joint Dept. of Biomedical Eng., Marquette Univ. and Med. Coll. of Wisconsin（马基特大学与威斯康星医学院联合生物医学工程系）
Diffusion-Driven Inertial Generated Data for Smartphone Location Classification
The Hatter Department of Marine Technologies, University of Haifa, Israel（海洋技术系，海法大学，以色列）；The Department of Information Systems, University of Haifa, Israel（信息系统系，海法大学，以色列）
SpectralDiff: A Generative Framework for Hyperspectral Image Classification with Diffusion Models
Peking University（北京大学）；Central South University（中南大学）；Hunan University（湖南大学）；Peng Cheng Laboratory（鹏城实验室）；Changsha University of Science and Technology（长沙理工大学）
University of Cambridge（剑桥大学）；Universite de Bordeaux（波尔多大学）
The automatic early diagnosis of prodromal stages of Alzheimer's disease is of great relevance for patient treatment to improve quality of life. We address this problem as a multi-modal classification task. Multi-modal data provides richer and complementary information. However, existing techniques only consider either lower order relations between the data and single/multi-modal imaging data. In this work, we introduce a novel semi-supervised hypergraph learning framework for Alzheimer's disease diagnosis. Our framework allows for higher-order relations among multi-modal imaging and non-imagi…
Despite continued advancement in recent years, deep neural networks still rely on large amounts of training data to avoid overfitting. However, labeled training data for real-world applications such as healthcare is limited and difficult to access given longstanding privacy, and strict data sharing policies. By manipulating image datasets in the pixel or feature space, existing data augmentation techniques represent one of the effective ways to improve the quantity and diversity of training data. Here, we look to advance augmentation techniques by building upon the emerging success of text-to-…
A Simple and Efficient Baseline for Zero-Shot Generative Classification
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Tsinghua University（清华大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Baidu（百度）
Improving Robustness and Reliability in Medical Image Classification with Latent-Guided Diffusion and Nested-Ensembles
McGill University（麦吉尔大学）；Centre for Intelligent Machines（智能机器中心）；Mila – Quebec AI Institute（魁北克人工智能研究所）；University of Copenhagen（哥本哈根大学）；Department of Public Health, Section for Health Data Science and AI（公共卫生系，健康数据科学与人工智能部门）
Derm-T2IM: Harnessing Synthetic Skin Lesion Data via Stable Diffusion Models for Enhanced Skin Disease Classification using ViT and CNN
College of Science and Engineering, University of Galway（戈尔韦大学科学与工程学院）；School of Computer Science, University of Galway（戈尔韦大学计算机科学学院）；Trinity College Dublin, the University of Dublin（都柏林大学圣三一学院）；St James’s Hospital（圣詹姆斯医院）
本文提出 Derm-T2IM，用调优的 Stable Diffusion 生成多样化皮肤镜病变图像，并验证其可增强 CNN 与 ViT 在两个真实数据集上的分类鲁棒性和泛化性。
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Georgia Tech（佐治亚理工学院）；University of Gondar（贡德尔大学）；Università della Svizzera Italiana（瑞士意大利语大学）；Google LLC（谷歌有限责任公司）；University of Amsterdam（阿姆斯特丹大学）；Stanford University（斯坦福大学）；Computational Design Institute（计算设计研究所）
Bridging Classification and Segmentation in Osteosarcoma Assessment via Foundation and Discrete Diffusion Models
Hanoi University of Science and Technology（河内科学技术大学）；Vinmec Times City International Hospital（Vinmec Times City国际医院）；Vinmec Healthcare System（Vinmec医疗系统）；VinUni-Illinois Smart Health Center（VinUni-伊利诺伊智能健康中心）；College of Health Sciences, VinUniversity（VinUniversity健康科学学院）
Knowledge-guided Complex Diffusion Model for PolSAR Image Classification in Contourlet Domain
Department of Computer Science and Technology, Shaanxi Key Laboratory for Network Computing and Security Technology, Xi’an University of Technology（计算机科学与技术系，陕西省网络计算与安全技术重点实验室，西安理工大学）；School of Computer Science and Technology, China University of Mining and Technology（计算机科学与技术学院，中国矿业大学）；School of Computer Science and Engineering, Nanyang Technological University（计算机科学与工程学院，南洋理工大学）
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；McCombs School of Business（麦库姆斯商学院）
Learning the distribution of a continuous or categorical response variable $\boldsymbol y$ given its covariates $\boldsymbol x$ is a fundamental problem in statistics and machine learning. Deep neural network-based supervised learning algorithms have made great progress in predicting the mean of $\boldsymbol y$ given $\boldsymbol x$, but they are often criticized for their ability to accurately capture the uncertainty of their predictions. In this paper, we introduce classification and regression diffusion (CARD) models, which combine a denoising diffusion-based conditional generative model an…
MeDi: Metadata-Guided Diffusion Models for Mitigating Biases in Tumor Classification
Machine Learning Group, Technische Universität Berlin, Germany The Konrad Zuse School of Excellence in Learning；Intelligent Systems (ELIZA), Germany BIFOLD – Berlin Institute for the Foundations of Learning
UniDiff: Parameter-Efficient Adaptation of Diffusion Models for Land Cover Classification with Multi-Modal Remotely Sensed Imagery and Sparse Annotations
Harvard Medical School（哈佛医学院）；UT Austin Dell Medical School（德克萨斯大学奥斯汀分校戴尔医学院）
Dermatological classification algorithms developed without sufficiently diverse training data may generalize poorly across populations. While intentional data collection and annotation offer the best means for improving representation, new computational approaches for generating training data may also aid in mitigating the effects of sampling bias. In this paper, we show that DALL$\cdot$E 2, a large-scale text-to-image diffusion model, can produce photorealistic images of skin disease across skin types. Using the Fitzpatrick 17k dataset as a benchmark, we demonstrate that augmenting training d…
