Related references
Note: Only part of the references are listed.
Article
Computer Science, Information Systems
Xiao Luo et al.
Summary: Nearest neighbor search is a basic task in fields like computer vision and data mining, and hashing is a widely used method for its efficiency. Deep hashing methods, with the development of deep learning, show more advantages than traditional methods. In this survey, deep supervised hashing and deep unsupervised hashing algorithms are investigated in detail. Additionally, important topics such as semi-supervised deep hashing, domain adaption deep hashing, and multi-modal deep hashing are introduced, along with commonly used datasets and performance evaluation schemes.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2023)
Article
Computer Science, Artificial Intelligence
Alper Gungor et al.
Summary: AdaDiff, the first adaptive diffusion prior for MRI reconstruction, is proposed to improve performance and reliability against domain shifts. It leverages an efficient diffusion prior trained via adversarial mapping over large reverse diffusion steps. A two-phase reconstruction, including a rapid-diffusion phase and an adaptation phase, is executed to refine the result by updating the prior to minimize data-consistency loss.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Computer Science, Hardware & Architecture
Xiaoqing Zhang et al.
Summary: Convolutional Neural Networks (CNNs) have achieved great success in computer vision applications. However, most state-of-the-art CNNs are difficult to deploy on resource-constrained mobile devices due to high computation and memory requirements. In this study, we propose a lightweight neural network framework called Offline Mobile Content-Based Image Retrieval (OMCBIR) to address this issue. We introduce pointwise group convolution, channel shuffle, and convolutional attention module to the model, resulting in an extremely lightweight network called Attention-based Lightweight Network (ALNet). ALNet outperforms MobileNetV2 in terms of mean Average Precision (mAP) while reducing model parameters and size significantly.
Article
Computer Science, Interdisciplinary Applications
Muzaffer Ozbey et al.
Summary: Missing images can be imputed through source-to-target modality translation to enhance diversity in medical imaging protocols. SynDiff, a novel method based on adversarial diffusion modeling, offers superior performance in medical image translation by progressively mapping noise and source images onto the target image.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2023)
Article
Computer Science, Software Engineering
Debanjan Pathak et al.
Summary: This article proposes an innovative image retrieval method by combining deep learning features from GoogleNet and low-level features from HSI and RGB color space. The proposed method achieves the best performance in terms of various performance parameters on multiple image datasets.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2022)
Article
Engineering, Electrical & Electronic
Weicheng Xie et al.
Summary: This paper proposes a new triplet loss method based on class-pair margins and multistage outlier suppression for facial expression recognition. This method can adapt to variations among different expression pairs and exclude difficult samples during triplet selection, improving the generalization performance of network features.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Yilan Zhang et al.
Summary: In this study, a dermoscopic image retrieval algorithm using convolutional neural networks and hash coding is designed. A hybrid dilated convolution spatial attention module and a Cauchy rotation invariance loss function are proposed to enhance the performance of the retrieval. Extensive experiments validate the effectiveness and versatility of the proposed module, algorithm, and loss function in dermoscopic image retrieval.
MEDICAL IMAGE ANALYSIS
(2022)
Article
Computer Science, Artificial Intelligence
Zhi Yu et al.
Summary: Person re-identification is widely used in intelligent monitoring to identify the same person across different cameras. The proposed TriEP loss improves the performance of person re-identification by giving attention to the hardest and other samples.
NEURAL PROCESSING LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Shiv Ram Dubey
Summary: This paper is a comprehensive survey of deep learning based developments in content based image retrieval over the past decade. It categorizes and performs a performance analysis on existing state-of-the-art methods, providing insights for researchers to observe progress and make optimal choices.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Biomedical
Nicolas Loiseau-Witon et al.
Summary: The study introduces a new method to learn a 3D keypoint descriptor by generating semi-synthetic training data and utilizing CNN with triplet loss for training. Experiments demonstrate the superiority of this method over hand-crafted descriptors and traditional 3D-SURF descriptors in terms of performance.
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
(2022)
Article
Computer Science, Artificial Intelligence
Noam Malali et al.
Summary: This paper presents a deep learning approach for learning joint semantic embeddings of images and captions in a euclidean space. The semantic similarity is approximated by the L-2 distances in the embedding space. The proposed scheme incorporates multitask learning, center loss, differentiable quantization scheme, and adaptive margin hinge loss to achieve favorable results.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Interdisciplinary Applications
Onat Dalmaz et al.
Summary: This paper proposes a novel generative adversarial approach, ResViT, which combines the contextual sensitivity of vision transformers, the precision of convolution operators, and the realism of adversarial learning. Demonstrations show that ResViT outperforms competing methods based on CNNs and transformers in terms of qualitative observations and quantitative metrics.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Computer Science, Information Systems
Saban Ozturk et al.
Summary: This paper presents a deep clustering approach for the detection of melanoma, using image embeddings to achieve clustering and addressing the issue of imbalanced samples in skin lesion databases.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Meenakshi Garg et al.
Summary: This paper introduces a content-based image retrieval technique which focuses on extraction and reduction in multiple features. Utilizing methods such as discrete wavelet transformation and local binary patterns, it achieves better results in texture image classification.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Biology
Walid Barhoumi et al.
Summary: The Content-Based Dermatological Lesion Retrieval (CBDLR) system retrieves similar skin lesion images with pathology-confirmed diagnosis to provide intuitive support for both inexperienced and experienced dermatologists, leading to early diagnosis and improved patient survival. The system proposed in the study integrates a similarity measure recommender for dynamic selection of distance metrics, utilizing deep-learned features and automatic generation of ground truth. Evaluation on challenging datasets demonstrates superior performance compared to standard CBDLR systems.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Computer Science, Artificial Intelligence
Daming Shi et al.
Summary: This paper presents a novel conditional Triplet loss to address few-shot learning problems, improving training speed and performance.
Article
Computer Science, Artificial Intelligence
Jitesh Pradhan et al.
Summary: This paper presents a novel feature extraction and fusion scheme based on regions-of-attention (ROA) to address the semantic challenges in image retrieval and consider the positional significance of different regions in the image. By combining ROA and non-ROA features, a retrieval scheme is proposed to support positional invariance in various sub-regions.
APPLIED SOFT COMPUTING
(2021)
Article
Engineering, Biomedical
Saban Ozturk
Summary: Medical imaging provides convenience for physicians to analyze diseases and increasing technological developments require effective indexing and retrieval systems for medical images.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Computer Science, Artificial Intelligence
Saban Ozturk et al.
Summary: The widespread use of medical imaging devices allows deep analysis of diseases, but increases the burden of specialist doctors. Computer-assisted systems provide an effective management tool for automatic analysis of these images, and there is a clear need for content-based image retrieval systems in hospitals for quick access and storage of large amounts of data.
TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES
(2021)
Article
Computer Science, Information Systems
Zheng Jiang et al.
IEEE TRANSACTIONS ON MULTIMEDIA
(2020)
Article
Biology
S. Deepak et al.
COMPUTERS IN BIOLOGY AND MEDICINE
(2020)
Review
Engineering, Multidisciplinary
Afshan Latif et al.
MATHEMATICAL PROBLEMS IN ENGINEERING
(2019)
Article
Computer Science, Artificial Intelligence
Syed Sameed Husain et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2019)
Article
Computer Science, Information Systems
De Cheng et al.
MULTIMEDIA TOOLS AND APPLICATIONS
(2018)
Article
Computer Science, Artificial Intelligence
T. Bui et al.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Gao Huang et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Weihua Chen et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Review
Computer Science, Artificial Intelligence
Edward Rosten et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2010)