no code implementations • 19 Apr 2024 • Marius Schmidt-Mengin, Alexis Benichoux, Shibeshih Belachew, Nikos Komodakis, Nikos Paragios
We apply it to weakly supervised medical image segmentation by training the 2D encoder to output high values for slices containing the regions of interest.
1 code implementation • 1 Dec 2023 • Ioannis Kakogeorgiou, Spyros Gidaris, Konstantinos Karantzalos, Nikos Komodakis
Unsupervised object-centric learning aims to decompose scenes into interpretable object entities, termed slots.
no code implementations • 18 Jul 2023 • Spyros Gidaris, Andrei Bursuc, Oriane Simeoni, Antonin Vobecky, Nikos Komodakis, Matthieu Cord, Patrick Pérez
Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks for very large fully-annotated datasets.
1 code implementation • 23 Mar 2022 • Ioannis Kakogeorgiou, Spyros Gidaris, Bill Psomas, Yannis Avrithis, Andrei Bursuc, Konstantinos Karantzalos, Nikos Komodakis
In this work, we argue that image token masking differs from token masking in text, due to the amount and correlation of tokens in an image.
2 code implementations • CVPR 2021 • Spyros Gidaris, Andrei Bursuc, Gilles Puy, Nikos Komodakis, Matthieu Cord, Patrick Pérez
With this in mind, we propose a teacher-student scheme to learn representations by training a convolutional net to reconstruct a bag-of-visual-words (BoW) representation of an image, given as input a perturbed version of that same image.
Ranked #18 on Semi-Supervised Image Classification on ImageNet - 1% labeled data (Top 5 Accuracy metric)
1 code implementation • CVPR 2020 • Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, Matthieu Cord
Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially dense image descriptions that encode discrete visual concepts, here called visual words.
1 code implementation • ECCV 2020 • Himalaya Jain, Spyros Gidaris, Nikos Komodakis, Patrick Pérez, Matthieu Cord
Knowledge distillation refers to the process of training a compact student network to achieve better accuracy by learning from a high capacity teacher network.
no code implementations • 12 Aug 2019 • Aakanksha Rana, Praveer Singh, Giuseppe Valenzise, Frederic Dufaux, Nikos Komodakis, Aljosa Smolic
In this paper, we address this problem by proposing a fast, parameter-free and scene-adaptable deep tone mapping operator (DeepTMO) that yields a high-resolution and high-subjective quality tone mapped output.
1 code implementation • ICCV 2019 • Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, Matthieu Cord
Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data.
1 code implementation • CVPR 2019 • Spyros Gidaris, Nikos Komodakis
The meta-model, given as input some novel classes with few training examples per class, must properly adapt the existing recognition model into a new model that can correctly classify in a unified way both the novel and the base classes.
1 code implementation • 28 Dec 2018 • Xu Shell Hu, Sergey Zagoruyko, Nikos Komodakis
We propose several ways to impose local symmetry in recurrent and convolutional neural networks, and show that our symmetry parameterizations satisfy universal approximation property for single hidden layer networks.
1 code implementation • 17 Sep 2018 • Edouard Oyallon, Sergey Zagoruyko, Gabriel Huang, Nikos Komodakis, Simon Lacoste-Julien, Matthew Blaschko, Eugene Belilovsky
In particular, by working in scattering space, we achieve competitive results both for supervised and unsupervised learning tasks, while making progress towards constructing more interpretable CNNs.
4 code implementations • CVPR 2018 • Spyros Gidaris, Nikos Komodakis
In this context, the goal of our work is to devise a few-shot visual learning system that during test time it will be able to efficiently learn novel categories from only a few training data while at the same time it will not forget the initial categories on which it was trained (here called base categories).
Ranked #2 on Few-Shot Image Classification on ImageNet (1-shot)
20 code implementations • ICLR 2018 • Spyros Gidaris, Praveer Singh, Nikos Komodakis
However, in order to successfully learn those features, they usually require massive amounts of manually labeled data, which is both expensive and impractical to scale.
Ranked #126 on Self-Supervised Image Classification on ImageNet
1 code implementation • ICLR 2018 • Martin Simonovsky, Nikos Komodakis
Deep learning on graphs has become a popular research topic with many applications.
no code implementations • CVPR 2017 • Hariprasad Kannan, Nikos Komodakis, Nikos Paragios
Linear programming relaxations are central to {\sc map} inference in discrete Markov Random Fields.
3 code implementations • 1 Jun 2017 • Sergey Zagoruyko, Nikos Komodakis
Deep neural networks with skip-connections, such as ResNet, show excellent performance in various image classification benchmarks.
2 code implementations • CVPR 2017 • Martin Simonovsky, Nikos Komodakis
A number of problems can be formulated as prediction on graph-structured data.
3 code implementations • ICCV 2017 • Diego Marcos, Michele Volpi, Nikos Komodakis, Devis Tuia
In many computer vision tasks, we expect a particular behavior of the output with respect to rotations of the input image.
Ranked #8 on Multi-tissue Nucleus Segmentation on Kumar
Breast Tumour Classification Colorectal Gland Segmentation: +5
1 code implementation • CVPR 2017 • Spyros Gidaris, Nikos Komodakis
Instead, we propose a generic architecture that decomposes the label improvement task to three steps: 1) detecting the initial label estimates that are incorrect, 2) replacing the incorrect labels with new ones, and finally 3) refining the renewed labels by predicting residual corrections w. r. t.
6 code implementations • 12 Dec 2016 • Sergey Zagoruyko, Nikos Komodakis
Attention plays a critical role in human visual experience.
Ranked #39 on Knowledge Distillation on ImageNet
no code implementations • 17 Sep 2016 • Martin Simonovsky, Benjamín Gutiérrez-Becker, Diana Mateus, Nassir Navab, Nikos Komodakis
Multimodal registration is a challenging problem in medical imaging due the high variability of tissue appearance under different imaging modalities.
no code implementations • 9 Aug 2016 • Martin Simonovsky, Nikos Komodakis
The focus of our work is speeding up evaluation of deep neural networks in retrieval scenarios, where conventional architectures may spend too much time on negative examples.
1 code implementation • 14 Jun 2016 • Spyros Gidaris, Nikos Komodakis
We extensively evaluate our AttractioNet approach on several image datasets (i. e. COCO, PASCAL, ImageNet detection and NYU-Depth V2 datasets) reporting on all of them state-of-the-art results that surpass the previous work in the field by a significant margin and also providing strong empirical evidence that our approach is capable to generalize to unseen categories.
71 code implementations • 23 May 2016 • Sergey Zagoruyko, Nikos Komodakis
Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance.
Ranked #12 on Image Classification on SVHN
1 code implementation • ICCV 2015 • Spyros Gidaris, Nikos Komodakis
We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features.
no code implementations • ICCV 2015 • Wenbin Zou, Nikos Komodakis
This leads to a rich feature representation, which is able to represent the context of the whole object/background and is much more discriminative as well as robust for salient object detection.
1 code implementation • CVPR 2016 • Spyros Gidaris, Nikos Komodakis
We propose a novel object localization methodology with the purpose of boosting the localization accuracy of state-of-the-art object detection systems.
1 code implementation • 7 May 2015 • Spyros Gidaris, Nikos Komodakis
We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features.
1 code implementation • CVPR 2015 • Sergey Zagoruyko, Nikos Komodakis
In this paper we show how to learn directly from image data (i. e., without resorting to manually-designed features) a general similarity function for comparing image patches, which is a task of fundamental importance for many computer vision problems.
no code implementations • NeurIPS 2014 • Bruno Conejo, Nikos Komodakis, Sebastien Leprince, Jean Philippe Avouac
We propose a general and versatile framework that significantly speeds-up graphical model optimization while maintaining an excellent solution accuracy.
no code implementations • 20 Jun 2014 • Nikos Komodakis, Jean-Christophe Pesquet
Optimization methods are at the core of many problems in signal/image processing, computer vision, and machine learning.
no code implementations • CVPR 2014 • Aristotle Spyropoulos, Nikos Komodakis, Philippos Mordohai
While machine learning has been instrumental to the ongoing progress in most areas of computer vision, it has not been applied to the problem of stereo matching with similar frequency or success.
no code implementations • 2 Apr 2014 • Jörg H. Kappes, Bjoern Andres, Fred A. Hamprecht, Christoph Schnörr, Sebastian Nowozin, Dhruv Batra, Sungwoong Kim, Bernhard X. Kausler, Thorben Kröger, Jan Lellmann, Nikos Komodakis, Bogdan Savchynskyy, Carsten Rother
However, on new and challenging types of models our findings disagree and suggest that polyhedral methods and integer programming solvers are competitive in terms of runtime and solution quality over a large range of model types.
1 code implementation • NeurIPS 2008 • Nikos Komodakis, Nikos Paragios, Georgios Tziritas
To deal with the most critical issue in a center-based clustering algorithm (selection of cluster centers), we also introduce the notion of stability of a cluster center, which is a well defined LP-based quantity that plays a key role to our algorithm's success.