1 code implementation • 15 Jan 2024 • Jakob Hackstein, Gencer Sumbul, Kai Norman Clasen, Begüm Demir
We finally derive a guideline to exploit masked image modeling for uni-modal and cross-modal CBIR problems in RS.
no code implementations • 10 Nov 2023 • Barış Büyüktaş, Gencer Sumbul, Begüm Demir
To this end, we initially provide a systematic review of the FL algorithms presented in the computer vision community for image classification problems, and select several state-of-the-art FL algorithms based on their effectiveness with respect to training data heterogeneity across clients (known as non-IID data).
no code implementations • 20 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.
no code implementations • 14 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.
no code implementations • 1 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.
1 code implementation • 2 Dec 2022 • Gencer Sumbul, Begüm Demir
Our approach aims to model the complementary characteristics of discriminative and generative reasoning for IRL under noisy labels.
no code implementations • 2 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.
no code implementations • 23 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.
no code implementations • 23 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.
no code implementations • 17 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.
no code implementations • 1 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.
no code implementations • 17 May 2021 • Gencer Sumbul, Arne de Wall, Tristan Kreuziger, Filipe Marcelino, Hugo Costa, Pedro Benevides, Mário Caetano, Begüm Demir, Volker Markl
In our experiments, we show the potential of BigEarthNet-MM for multi-modal multi-label image retrieval and classification problems by considering several state-of-the-art DL models.
1 code implementation • 8 May 2021 • Gencer Sumbul, Mahdyar Ravanbakhsh, Begüm Demir
The proposed method selects a small set of the most representative and informative triplets based on two main steps.
no code implementations • 29 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.
no code implementations • 20 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.
no code implementations • 15 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.
no code implementations • 3 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.
no code implementations • 17 Jan 2020 • Gencer Sumbul, Jian Kang, Tristan Kreuziger, Filipe Marcelino, Hugo Costa, Pedro Benevides, Mario Caetano, Begüm Demir
This is achieved by interpreting and arranging the CLC Level-3 nomenclature based on the properties of Sentinel-2 images in a new nomenclature of 19 classes.
no code implementations • 12 Dec 2019 • Kexin Zhang, Gencer Sumbul, Begüm Demir
Then, we formulate the adversarial learning of the generator and discriminator networks as a min-max game.
no code implementations • 28 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.
no code implementations • 16 Feb 2019 • Gencer Sumbul, Marcela Charfuelan, Begüm Demir, Volker Markl
This paper presents the BigEarthNet that is a new large-scale multi-label Sentinel-2 benchmark archive.
no code implementations • 18 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.
no code implementations • 9 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.