0% Complete
صفحه اصلی
/
سی و دومین کنفرانس بین المللی مهندسی برق
High-Resolution Remote Sensing Image Captioning Based on Structured Attention and SAM Network
نویسندگان :
Yassin Riyazi
1
Seyyed Mostafa Sadjadi
2
Abbas Zohrevand
3
Reshad Hosseini
4
1- دانشگاه تهران
2- دانشگاه تهران
3- دانشگاه تهران
4- دانشگاه تهران
کلمات کلیدی :
image captioning،image segmentation،remote sensing image،structured attention
چکیده :
Due to its broad applications, remote sensing image captioning (RSIC) has gained popularity in recent years. However, it poses extra challenges for containing low-resolution images with highly structured semantic content. By incorporating image labeling and segmentation, this work expands on the RSIC framework developed by Zhao et al. [1]. The method presents a structured attention module that highlights important semantic components to maintain a geometric and structured shape. The quality and edge emphasis of UCM-captioned photographs is improved by upsampling them to 512×512 pixels. Using the Segment Anything Model (SAM) produces better image proposals, leading to higher accuracy than traditional techniques. A balanced output of large- and small-object masks is facilitated by SAM's promptability. The decoder can more easily learn a suitable statistical model using the model's spatial structure to provide an all-encompassing attention map. The effects of multiple hyperparameters, such as teacher forcing, the number of region proposals, and the effects of DSR and AVR loss factors, are investigated in this work. Overall, by combining image labeling and segmentation, this research improves remote sensing capabilities. It also shows how well the structured attention module and SAM work together to improve accuracy and consider different hyperparameter issues.
لیست مقالات
لیست مقالات بایگانی شده
Total Transfer Capability Improvement Using High Temperature Low Sag Conductors
Seyed Sina Mousavi-Seyedi - Mohammad Reza Rezaei - Mohammad Reza Miveh
Multi-Octave Continuous Mode Power Amplifier with More Than 46 dBm Peak Output Power
Marzieh Chegini - Mahmoud Kamarei
Underwater Image Quality Assessment via Color and Contrast Analysis
Meysam Ghalyani - Maryam Karimi
A Novel PM-Assisted Linear Switched Reluctance Motor
Matin Vatani - Mojtaba Mirsalim - Javad Shokrollahi Moghani
Study of Performance Characteristics of a Line-Start Synchronous Reluctance Motor Over its Synchronization Region
Ali Jamali-Fard - Mojtaba Mirsalim
طبقهبندی تصاویر سلولی پاپ اسمیر مبتنی بر الگوریتمهای ترتیبی یادگیری جمعی و شبکههای عمیق استخراج ویژگی
زهرا کمالی - محمدصادق هل فروش - کامران کاظمی - مژگان اکبرزاده
Entanglement-Assisted Classical-Quantum Multiple Access Wiretap Channel: One-shot Achievable Rate Region
Hadi Aghaee - Bahareh Akhbari
CNN-LSTM model for Confusion Classification; using Single-Channel EEG
Amirhossein Aran - Zahra Ghanbari - Mohammad Hassan Moradi
Realization of a high-resolution plasmonic refractive index sensor based on double-nanodisk shaped resonators
Leila Hajshahvaladi - Hassan Kaatuzian - Mohammad Danaie - Ghazaleh Nourbakhsh
Precise model extraction for Li-Ion batteries using segmented Columb counting and Kalman filtering
Ali Fotokkiani - Ali Ghanbarian - Amirhossein Esteghamat - Ali Fotowat-Ahmady - Farzad Tahami
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.3