IEEE

Cross-Domain Incremental Image Classification via Domain-Specific Prototypes and Contrastive Learning

Abstract: Remote sensing models in incremental learning (IL) scenarios often need to contend with both the newly emerged classes and cross-domain feature shifts, a combined challenge that we name it ...
IEEE

Deep Learning-Driven Image Classification of Jellyfish: A CNN Model Approach

Abstract: Rising in importance as an environmental problem, jellyfish blooms impair aquaculture infrastructure, upset marine ecosystems, and reveal human health risks. Good early reaction and ...
IEEE

MCBL-UNet: A Hybrid Mamba-CNN Boundary Enhanced Light-weight UNet for Placenta Ultrasound Image Segmentation

Abstract: The shape and size of the placenta are closely related to fetal development in the second and third trimesters of pregnancy. Accurately segmenting the placental contour in ultrasound images ...
IEEE

iNatAg: Multi-Class Classification Models Enabled by a Large-Scale Benchmark Dataset with 4.7M Images of 2,959 Crop and Weed Species

Abstract: Accurate identification of crop and weed species is critical for precision agriculture and sustainable farming. However, it remains challenging due to visual similarity among species, ...
IEEE

Fault Classification in Hybrid Microgrid Using Semi-Supervised CNN

Abstract: As renewable energy sources (RESs) are increasingly used in power systems, hybrid microgrids offer a flexible solution to improve grid stability, reliability, and efficiency. However, their ...
IEEE

Transformer-Embedded Attentive CNN for Spectral Image Analysis of Rice Blast Syndromes

Abstract: Leaf blast disease is a significant constraint in world-wide rice production systems, necessitating effective monitoring for optimized crop-yield management. Satellite-derived land-surface ...
IEEE

A Heterogeneous CNN with Transformers for Image Denoising

Abstract: Deep learning models often emphasize structural information over long-range dependencies when producing cleaner images. To enhance the robustness of the resulting denoisers, this work ...
IEEE

Enhancing GNSS Localization in Urban Canyons With a Hybrid CNN-Autoencoder Approach to LOS/NLOS Classification

Abstract: Non-Line-of-Sight (NLOS) reception is acknowledged as a primary source of positioning error in Global Navigation Satellite System (GNSS) applications ...
IEEE

Domain-Aware Adversarial Domain Augmentation Network for Hyperspectral Image Classification

Abstract: Classifying hyperspectral remote sensing images across different scenes has recently emerged as a significant challenge. When only historical labeled images (source domain, SD) are available ...
IEEE

UAV Image Classification: A Comparative Evaluation of CNN Models

Abstract: Aerial image classification plays a vital role in applications such as building footprint extraction, water/soil analysis, 3D reconstruction. Accurate classification enables timely ...
IEEE

Hybrid ResNet-ViT Transfer Learning Approach for Brain Stroke Classification on Computed Tomography Images

Abstract: This study investigates the utilization of a hybrid Convolutional Neural Network (CNN) and Vision Transformer (ViT) model, employing transfer learning methods, to enhance brain stroke ...
IEEE

A Lightweight Spatial–Spectral Deformable CNN for UAV Hyperspectral Image Classification

Abstract: In recent years, uncrewed aerial vehicle (UAV) technology has shown great potential for application in hyperspectral image (HSI) classification tasks due to its advantages of flexible ...