Ioannis Kakogeorgiou

Dr. Ioannis Kakogeorgiou

Institute of Informatics and Telecommunications, National Centre of Scientific Research "Demokritos", Athens, Attikí, Greece
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2021 in International Journal of Applied Earth Observation and Geoinformation
Verified
Journal Article
Open access
Ioannis KakogeorgiouIoannis Kakogeorgiou
Ioannis Kakogeorgiou
Konstantinos KarantzalosKonstantinos Karantzalos
Konstantinos Karantzalos

3 November 2022
Verified
Book Chapter
Closed access
PDF file
Ioannis KakogeorgiouIoannis Kakogeorgiou
Ioannis Kakogeorgiou
SGSpyros Gidaris
Spyros Gidaris
BPBill Psomas
Bill Psomas
YAYannis Avrithis
Yannis Avrithis
ABAndrei Bursuc
Andrei Bursuc
NKNikos Komodakis
Nikos Komodakis

7 January 2022 in PLOS ONE
Verified
Journal Article
Open access
PDF file
Katerina KikakiKaterina Kikaki
Katerina Kikaki
Ioannis KakogeorgiouIoannis Kakogeorgiou
Ioannis Kakogeorgiou
PMParaskevi Mikeli
Paraskevi Mikeli
Dionysios RaitsosDionysios Raitsos
Dionysios Raitsos
KKKonstantinos Karantzalos
Konstantinos Karantzalos
Currently, a significant amount of research is focused on detecting Marine Debris and assessing its spectral behaviour via remote sensing, ultimately aiming at new operational monitoring solutions. Here, we introduce a Marine Debris Archive (MARIDA), as a benchmark dataset for developing and evaluating Machine Learning (ML) algorithms capable of detecting Marine Debris. MARIDA is the first dataset based on the multispectral Sentinel-2 (S2) satellite data, which distinguishes Marine Debris from various marine features that co-exist, includingSargassum macroalgae,Ships,Natural Organic Material,Waves,Wakes,Foam, dissimilar water types (i.e.,Clear,Turbid Water,Sediment-Laden Water,Shallow Water), andClouds. We provide annotations (georeferenced polygons/ pixels) from verified plastic debris events in several geographical regions globally, during different seasons, years and sea state conditions. A detailed spectral and statistical analysis of the MARIDA dataset is presented along with well-established ML baselines for weakly supervised semantic segmentation and multi-label classification tasks. MARIDA is an open-access dataset which enables the research community to explore the spectral behaviour of certain floating materials, sea state features and water types, to develop and evaluate Marine Debris detection solutions based on artificial intelligence and deep learning architectures, as well as satellite pre-processing pipelines.

7 March 2024 in ISPRS Journal of Photogrammetry and Remote Sensing
Verified
Journal Article
Open access
Katerina KikakiKaterina Kikaki
Katerina Kikaki
Ioannis KakogeorgiouIoannis Kakogeorgiou
Ioannis Kakogeorgiou
IHIbrahim Hoteit
Ibrahim Hoteit
KKKonstantinos Karantzalos
Konstantinos Karantzalos
1

16 June 2024
Verified
Conference Paper
Closed access
Ioannis KakogeorgiouIoannis Kakogeorgiou
Ioannis Kakogeorgiou
SGSpyros Gidaris
Spyros Gidaris
KKKonstantinos Karantzalos
Konstantinos Karantzalos
NKNikos Komodakis
Nikos Komodakis
Unsupervised object-centric learning aims to decompose scenes into interpretable object entities, termed slots. Slot-based auto-encoders stand out as a prominent method for this task. Within them, crucial aspects include guiding the encoder to generate object-specific slots and ensuring the decoder utilizes them during reconstruction. This work introduces two novel techniques, (i) an attention-based self-training approach, which distills superior slot-based attention masks from the decoder to the encoder, enhancing object segmentation, and (ii) an innovative patch-order permutation strategy for autoregressive transformers that strengthens the role of slot vectors in reconstruction. The effectiveness of these strategies is showcased experimentally. The combined approach significantly surpasses prior slot-based autoencoder methods in unsupervised object segmentation, especially with complex real-world images. We provide the implementation code at https://github.com/gkakogeorgiou/spot.

1 October 2023
Verified
Conference Paper
Closed access
BPBill Psomas
Bill Psomas
Ioannis KakogeorgiouIoannis Kakogeorgiou
Ioannis Kakogeorgiou
KKKonstantinos Karantzalos
Konstantinos Karantzalos
YAYannis Avrithis
Yannis Avrithis
Convolutional networks and vision transformers have different forms of pairwise interactions, pooling across layers and pooling at the end of the network. Does the latter really need to be different? As a by-product of pooling, vision transformers provide spatial attention for free, but this is most often of low quality unless self-supervised, which is not well studied. Is supervision really the problem?In this work, we develop a generic pooling framework and then we formulate a number of existing methods as instantiations. By discussing the properties of each group of methods, we derive SimPool, a simple attention-based pooling mechanism as a replacement of the default one for both convolutional and transformer encoders. We find that, whether supervised or self-supervised, this improves performance on pre-training and downstream tasks and provides attention maps delineating object boundaries in all cases. One could thus call SimPool universal. To our knowledge, we are the first to obtain attention maps in supervised transformers of at least as good quality as self-supervised, without explicit losses or modifying the architecture. Code at: https://github.com/billpsomas/simpool.