A5053152871- Remote-Sensing Image Classification
- Automated Road and Building Extraction
- Domain Adaptation and Few-Shot Learning
- EEG and Brain-Computer Interfaces
- Radiomics and Machine Learning in Medical Imaging
- Remote Sensing and LiDAR Applications
- AI in cancer detection
- Advanced Image Fusion Techniques
- Olfactory and Sensory Function Studies
- Advanced Vision and Imaging
- COVID-19 diagnosis using AI
- Geochemistry and Geologic Mapping
- Muscle activation and electromyography studies
- Digital Imaging for Blood Diseases
- Visual Attention and Saliency Detection
- Sparse and Compressive Sensing Techniques
- Blind Source Separation Techniques
- Neural Networks and Applications
- Aesthetic Perception and Analysis
- Neuroscience and Neural Engineering
- Image and Signal Denoising Methods
- Advanced Image Processing Techniques
Technical University of Munich
2023-2024
Jadavpur University
2021-2022
The notion of self and cross-attention learning has been found to substantially boost the performance remote sensing (RS) image fusion. However, while self-attention models fail incorporate global context due limited size receptive fields, may generate ambiguous features as feature extractors for all modalities are jointly trained. This results in generation redundant multi-modal features, thus limiting fusion performance. To address these issues, we propose a novel architecture called...
In few-shot open-set recognition (FSOSR) for hyperspectral images (HSI), one major challenge arises due to the simultaneous presence of spectrally fine-grained known classes and outliers. Prior research on generative FSOSR cannot handle such a situation their inability approximate open space prudently. To address this issue, we propose method, Meta-learning-based Open-set Recognition via Generative Adversarial Network (MORGAN), that can learn finer separation between closed spaces. MORGAN...
Recent advancements in prototype-based Few-Shot Open-Set Recognition (FSOSR) approaches reject outliers based on the high metric distances from <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">known</i> class prototypes and fail to distinguish spectrally fine-grained land cover outliers. Learning only Euclidean distance fit spherical distributions ignores essential distribution parameters like shift, shape, scale. The conventional...
Scientific creativity refers to the exhibition of original ideas in various domains science that promotes technological progress. Aesthetic sensibility, ability comprehend visual appeal any object, plays a significant role guiding cognitive process scientific creation. The present study attempts detect creative individuals field by analyzing their aesthetic quality judgment using Electroencephalographic (EEG) system. major aim current is accomplished first acquiring brain signals from...
Efficient road and building footprint extraction from satellite images are predominant in many remote sensing applications. However, precise segmentation map is quite challenging due to the diverse structures camouflaged by trees, similar spectral responses between roads buildings, occlusions heterogeneous traffic over roads. Existing convolutional neural network (CNN)-based methods focus on either enriched spatial semantics learning for or fine-grained topology extraction. The profound...
The paper introduces an innovative methodology for the automatic discrimination of multiple choice answers chosen by merit and random guess analyzing confidence level examinees using Electroencephalographic system. acquired brain signals subjects participating in experiment are first examined eLORETA software which portrays active participation middle frontal gyrus precuneus when a subject is fully confident regarding correct answer. In next phase, pre-processed converted to spectrogram...