Search Results for author: Gencer Sumbul

Found 23 papers, 3 papers with code

Federated Learning Across Decentralized and Unshared Archives for Remote Sensing Image Classification

no code implementations10 Nov 2023 Barış Büyüktaş, Gencer Sumbul, Begüm Demir

After presenting an extensive overview of the selected algorithms, a theoretical comparison of the algorithms is conducted based on their: 1) local training complexity; 2) aggregation complexity; 3) learning efficiency; 4) communication cost; and 5) scalability in terms of number of clients.

Federated Learning Multi-Label Classification +2

Annotation Cost Efficient Active Learning for Content Based Image Retrieval

no code implementations20 Jun 2023 Julia Henkel, Genc Hoxha, Gencer Sumbul, Lars Möllenbrok, Begüm Demir

Unlike the existing AL methods for CBIR, at each AL iteration of ANNEAL a human expert is asked to annotate the most informative image pairs as similar/dissimilar.

Active Learning Content-Based Image Retrieval +2

Label Noise Robust Image Representation Learning based on Supervised Variational Autoencoders in Remote Sensing

no code implementations14 Jun 2023 Gencer Sumbul, Begüm Demir

To address this issue, in this paper we propose a label noise robust IRL method that aims to prevent the interference of noisy labels on IRL, independently from the learning task being considered in RS.

Representation Learning

Learning Across Decentralized Multi-Modal Remote Sensing Archives with Federated Learning

no code implementations1 Jun 2023 Barış Büyüktaş, Gencer Sumbul, Begüm Demir

The MF module performs iterative model averaging to learn without accessing data on clients in the case that clients are associated with different data modalities.

Federated Learning Image Classification

Deep Active Learning for Multi-Label Classification of Remote Sensing Images

no code implementations2 Dec 2022 Lars Möllenbrok, Gencer Sumbul, Begüm Demir

Unlike the existing AL query functions (which are defined for single-label classification or semantic segmentation problems), each query function in this paper is based on the evaluation of two criteria: i) multi-label uncertainty; and ii) multi-label diversity.

Active Learning Clustering +2

Generative Reasoning Integrated Label Noise Robust Deep Image Representation Learning

1 code implementation2 Dec 2022 Gencer Sumbul, Begüm Demir

Our approach aims to model the complementary characteristics of discriminative and generative reasoning for IRL under noisy labels.

Representation Learning

A Novel Self-Supervised Cross-Modal Image Retrieval Method In Remote Sensing

no code implementations23 Feb 2022 Gencer Sumbul, Markus Müller, Begüm Demir

Due to the availability of multi-modal remote sensing (RS) image archives, one of the most important research topics is the development of cross-modal RS image retrieval (CM-RSIR) methods that search semantically similar images across different modalities.

Image Retrieval Retrieval

Deep Metric Learning-Based Semi-Supervised Regression With Alternate Learning

no code implementations23 Feb 2022 Adina Zell, Gencer Sumbul, Begüm Demir

The proposed DML-S2R method aims to mitigate the problems of insufficient amount of labeled samples without collecting any additional sample with a target value.

Metric Learning regression

A Novel Framework to Jointly Compress and Index Remote Sensing Images for Efficient Content-Based Retrieval

no code implementations17 Jan 2022 Gencer Sumbul, Jun Xiang, Nimisha Thekke Madam, Begüm Demir

We also introduce a two stage learning strategy with gradient manipulation techniques to obtain image representations that are compatible with both RS image indexing and compression.

Content-Based Image Retrieval Image Compression +1

A Novel Graph-Theoretic Deep Representation Learning Method for Multi-Label Remote Sensing Image Retrieval

no code implementations1 Jun 2021 Gencer Sumbul, Begüm Demir

Unlike the other graph-based methods, the proposed method contains a novel learning strategy to train a deep neural network for automatically predicting a graph structure of each RS image in the archive.

Image Retrieval Representation Learning +1

A Comparative Study of Deep Learning Loss Functions for Multi-Label Remote Sensing Image Classification

no code implementations29 Sep 2020 Hichame Yessou, Gencer Sumbul, Begüm Demir

This paper analyzes and compares different deep learning loss functions in the framework of multi-label remote sensing (RS) image scene classification problems.

General Classification Image Classification +2

Remote Sensing Image Scene Classification with Deep Neural Networks in JPEG 2000 Compressed Domain

no code implementations20 Jun 2020 Akshara Preethy Byju, Gencer Sumbul, Begüm Demir, Lorenzo Bruzzone

This is achieved by taking codestreams associated with the coarsest resolution wavelet sub-band as input to approximate finer resolution sub-bands using a number of transposed convolutional layers.

Classification General Classification +1

SD-RSIC: Summarization Driven Deep Remote Sensing Image Captioning

no code implementations15 Jun 2020 Gencer Sumbul, Sonali Nayak, Begüm Demir

The first step obtains the standard image captions by jointly exploiting convolutional neural networks (CNNs) with long short-term memory (LSTM) networks.

Image Captioning

Deep Learning for Image Search and Retrieval in Large Remote Sensing Archives

no code implementations3 Apr 2020 Gencer Sumbul, Jian Kang, Begüm Demir

This chapter presents recent advances in content based image search and retrieval (CBIR) systems in remote sensing (RS) for fast and accurate information discovery from massive data archives.

Deep Hashing Image Retrieval

A Novel Multi-Attention Driven System For Multi-Label Remote Sensing Image Classification

no code implementations28 Feb 2019 Gencer Sumbul, Begüm Demir

The first module aims to extract preliminary local descriptors of RS image bands that can be associated to different spatial resolutions.

General Classification Image Classification +1

Multisource Region Attention Network for Fine-Grained Object Recognition in Remote Sensing Imagery

no code implementations18 Jan 2019 Gencer Sumbul, Ramazan Gokberk Cinbis, Selim Aksoy

Fine-grained object recognition concerns the identification of the type of an object among a large number of closely related sub-categories.

General Classification Object Recognition

Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery

no code implementations9 Dec 2017 Gencer Sumbul, Ramazan Gokberk Cinbis, Selim Aksoy

Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data.

Language Modelling Object Recognition +2

Cannot find the paper you are looking for? You can Submit a new open access paper.