International Conference on Computer Vision and Image Processing最新文献

Effective-LDAM: An Effective Loss Function to Mitigate Data Imbalance for Robust Chest X-Ray Disease Classification Effective-LDAM：缓解数据失衡的有效损失函数，用于稳健的胸部 X 射线疾病分类

International Conference on Computer Vision and Image Processing Pub Date : 2024-07-06 DOI: 10.1007/978-3-031-58535-7_16

S. SreeRamaVamsidhar, Bhargava Satya, Rama Krishna Sai Subrahmanyam Gorthi

引用次数: 0

Deep Learning based Novel Cascaded Approach for Skin Lesion Analysis 基于深度学习的新型级联皮肤损伤分析方法

International Conference on Computer Vision and Image Processing Pub Date : 2023-01-16 DOI: 10.48550/arXiv.2301.06226

Shubham Innani, Prasad Dutande, B. Baheti, Ujjwal Baid, S. Talbar

引用次数: 3

SRTGAN: Triplet Loss based Generative Adversarial Network for Real-World Super-Resolution SRTGAN:基于三重损失的生成对抗网络，用于现实世界的超分辨率

International Conference on Computer Vision and Image Processing Pub Date : 2022-11-22 DOI: 10.48550/arXiv.2211.12180

Dhruv V. Patel, Abhinav Jain, S. Bawkar, Manav Khorasiya, Kalpesh P. Prajapati, Kishor P. Upla, K. Raja, Raghavendra Ramachandra, C. Busch

{"title":"SRTGAN: Triplet Loss based Generative Adversarial Network for Real-World Super-Resolution","authors":"Dhruv V. Patel, Abhinav Jain, S. Bawkar, Manav Khorasiya, Kalpesh P. Prajapati, Kishor P. Upla, K. Raja, Raghavendra Ramachandra, C. Busch","doi":"10.48550/arXiv.2211.12180","DOIUrl":"https://doi.org/10.48550/arXiv.2211.12180","url":null,"abstract":"Many applications such as forensics, surveillance, satellite imaging, medical imaging, etc., demand High-Resolution (HR) images. However, obtaining an HR image is not always possible due to the limitations of optical sensors and their costs. An alternative solution called Single Image Super-Resolution (SISR) is a software-driven approach that aims to take a Low-Resolution (LR) image and obtain the HR image. Most supervised SISR solutions use ground truth HR image as a target and do not include the information provided in the LR image, which could be valuable. In this work, we introduce Triplet Loss-based Generative Adversarial Network hereafter referred as SRTGAN for Image Super-Resolution problem on real-world degradation. We introduce a new triplet-based adversarial loss function that exploits the information provided in the LR image by using it as a negative sample. Allowing the patch-based discriminator with access to both HR and LR images optimizes to better differentiate between HR and LR images; hence, improving the adversary. Further, we propose to fuse the adversarial loss, content loss, perceptual loss, and quality loss to obtain Super-Resolution (SR) image with high perceptual fidelity. We validate the superior performance of the proposed method over the other existing methods on the RealSR dataset in terms of quantitative and qualitative metrics.","PeriodicalId":110299,"journal":{"name":"International Conference on Computer Vision and Image Processing","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129399171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Self Similarity Matrix based CNN Filter Pruning 基于自相似矩阵的CNN滤波器剪枝

International Conference on Computer Vision and Image Processing Pub Date : 2022-11-03 DOI: 10.48550/arXiv.2211.01814

S. Rakshith, Jayesh Rajkumar Vachhani, Sourabh Vasant Gothe, Rishabh Khurana

引用次数: 0

T2CI-GAN: Text to Compressed Image generation using Generative Adversarial Network T2CI-GAN:使用生成对抗网络生成文本到压缩图像

International Conference on Computer Vision and Image Processing Pub Date : 2022-10-01 DOI: 10.48550/arXiv.2210.03734

B. Rajesh, Nandakishore Dusa, M. Javed, S. Dubey, P. Nagabhushan

{"title":"T2CI-GAN: Text to Compressed Image generation using Generative Adversarial Network","authors":"B. Rajesh, Nandakishore Dusa, M. Javed, S. Dubey, P. Nagabhushan","doi":"10.48550/arXiv.2210.03734","DOIUrl":"https://doi.org/10.48550/arXiv.2210.03734","url":null,"abstract":"The problem of generating textual descriptions for the visual data has gained research attention in the recent years. In contrast to that the problem of generating visual data from textual descriptions is still very challenging, because it requires the combination of both Natural Language Processing (NLP) and Computer Vision techniques. The existing methods utilize the Generative Adversarial Networks (GANs) and generate the uncompressed images from textual description. However, in practice, most of the visual data are processed and transmitted in the compressed representation. Hence, the proposed work attempts to generate the visual data directly in the compressed representation form using Deep Convolutional GANs (DCGANs) to achieve the storage and computational efficiency. We propose GAN models for compressed image generation from text. The first model is directly trained with JPEG compressed DCT images (compressed domain) to generate the compressed images from text descriptions. The second model is trained with RGB images (pixel domain) to generate JPEG compressed DCT representation from text descriptions. The proposed models are tested on an open source benchmark dataset Oxford-102 Flower images using both RGB and JPEG compressed versions, and accomplished the state-of-the-art performance in the JPEG compressed domain. The code will be publicly released at GitHub after acceptance of paper.","PeriodicalId":110299,"journal":{"name":"International Conference on Computer Vision and Image Processing","volume":"105 7S 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124941069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Classroom Slide Narration System 课堂幻灯片叙述系统

International Conference on Computer Vision and Image Processing Pub Date : 2022-01-21 DOI: 10.1007/978-3-031-11349-9_12

K. V. Jobin, Ajoy Mondal, C. V. Jawahar

引用次数: 0

On-Device Spatial Attention based Sequence Learning Approach for Scene Text Script Identification 基于设备上空间注意的场景文本脚本识别序列学习方法

International Conference on Computer Vision and Image Processing Pub Date : 2021-12-01 DOI: 10.1007/978-3-031-11349-9_20

Rutika Moharir, Arun D Prabhu, Sukumar Moharana, Gopi Ramena, Rachit S Munjal

引用次数: 0

FMD-cGAN: Fast Motion Deblurring using Conditional Generative Adversarial Networks FMD-cGAN:使用条件生成对抗网络的快速运动去模糊

International Conference on Computer Vision and Image Processing Pub Date : 2021-11-30 DOI: 10.1007/978-3-031-11349-9_32

Jatin Kumar, Indra Deep Mastan, S. Raman

引用次数: 0

Scene Graph Generation with Geometric Context 具有几何上下文的场景图生成

International Conference on Computer Vision and Image Processing Pub Date : 2021-11-25 DOI: 10.1007/978-3-031-11346-8_30

Vishal Kumar, A. Mundu, S. Singh

引用次数: 0

A Novel Deep Learning Method for Thermal to Annotated Thermal-Optical Fused Images 一种新的深度学习方法用于热注释热光学融合图像

International Conference on Computer Vision and Image Processing Pub Date : 2021-07-13 DOI: 10.1007/978-3-031-31407-0_50

Suranjana Goswami, S. Singh, B. Chaudhuri

引用次数: 1