1 code implementation • 7 Jul 2023 • Vladan Stojnić, Zakaria Laskar, Giorgos Tolias
In this work, we present an approach that leverages three highly synergistic components, which are identified as key ingredients: joint classifier training with inliers and outliers, semi-supervised learning through pseudo-labeling, and model ensembling.
1 code implementation • 15 Jun 2023 • Ed Pizzi, Giorgos Kordopatis-Zilos, Hiral Patel, Gheorghe Postelnicu, Sugosh Nagavara Ravindra, Akshay Gupta, Symeon Papadopoulos, Giorgos Tolias, Matthijs Douze
The problem comprises two distinct but related tasks: determining whether a query video shares content with a reference video ("detection"), and additionally temporally localizing the shared content within each video ("localization").
no code implementations • 5 May 2023 • Shuzhe Wang, Zakaria Laskar, Iaroslav Melekhov, Xiaotian Li, Yi Zhao, Giorgos Tolias, Juho Kannala
In this work, we present a new hierarchical scene coordinate network to predict pixel scene coordinates in a coarse-to-fine manner from a single RGB image.
1 code implementation • 6 Apr 2023 • Giorgos Kordopatis-Zilos, Giorgos Tolias, Christos Tzelepis, Ioannis Kompatsiaris, Ioannis Patras, Symeon Papadopoulos
We introduce S$^2$VS, a video similarity learning approach with self-supervision.
no code implementations • 28 Mar 2023 • Juliette Bertrand, Yannis Kalantidis, Giorgos Tolias
Few-shot action recognition, i. e. recognizing new action classes given only a few examples, benefits from incorporating temporal information.
1 code implementation • 11 Oct 2022 • Pavel Suma, Giorgos Tolias
The goal is to obtain a network for database examples that is trained to operate on large resolution images and benefits from fine-grained image details, and a second network for query examples that operates on small resolution images but preserves a representation space aligned with that of the database network.
1 code implementation • 26 Feb 2022 • Nikos Efthymiadis, Giorgos Tolias, Ondrej Chum
To bridge the domain gap we present a novel augmentation technique that is tailored to the task of learning sketch recognition from a training set of natural images.
no code implementations • 8 Feb 2022 • Zoë Papakipos, Giorgos Tolias, Tomas Jenicek, Ed Pizzi, Shuhei Yokoo, Wenhao Wang, Yifan Sun, Weipu Zhang, Yi Yang, Sanjay Addicam, Sergio Manuel Papadakis, Cristian Canton Ferrer, Ondrej Chum, Matthijs Douze
The 2021 Image Similarity Challenge introduced a dataset to serve as a new benchmark to evaluate recent image copy detection methods.
no code implementations • 3 Feb 2022 • Nikolaos-Antonios Ypsilantis, Noa Garcia, Guangxing Han, Sarah Ibrahimi, Nanne van Noord, Giorgos Tolias
Testing is primarily performed on photos taken by museum guests depicting exhibits, which introduces a distribution shift between training and testing.
2 code implementations • CVPR 2022 • Yash Patel, Giorgos Tolias, Jiri Matas
This work focuses on learning deep visual representation models for retrieval by exploring the interplay between a new loss function, the batch size, and a new regularization approach.
Ranked #1 on
Vehicle Re-Identification
on VehicleID Small
1 code implementation • 17 Jun 2021 • Matthijs Douze, Giorgos Tolias, Ed Pizzi, Zoë Papakipos, Lowik Chanussot, Filip Radenovic, Tomas Jenicek, Maxim Maximov, Laura Leal-Taixé, Ismail Elezi, Ondřej Chum, Cristian Canton Ferrer
This benchmark is used for the Image Similarity Challenge at NeurIPS'21 (ISC2021).
Ranked #1 on
Image Similarity Detection
on DISC21 dev
1 code implementation • ECCV 2020 • Giorgos Tolias, Tomas Jenicek, Ondřej Chum
At inference, the local descriptors are provided by the activations of internal components of the network.
Ranked #5 on
Image Retrieval
on ROxford (Medium)
1 code implementation • ECCV 2020 • Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondrej Chum, Cordelia Schmid
In this work we consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given.
1 code implementation • ICCV 2019 • Giorgos Tolias, Filip Radenovic, Ondřej Chum
We show successful attacks to partially unknown systems, by designing various loss functions for the adversarial image construction.
no code implementations • CVPR 2019 • Arun Mukundan, Giorgos Tolias, Ondrej Chum
We evaluate the descriptor on standard benchmarks.
1 code implementation • CVPR 2019 • Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondrej Chum
In this work, we employ a transductive label propagation method that is based on the manifold assumption to make predictions on the entire dataset and use these predictions to generate pseudo-labels for the unlabeled data and train a deep neural network.
3 code implementations • 27 Nov 2018 • Arun Mukundan, Giorgos Tolias, Andrei Bursuc, Hervé Jégou, Ondřej Chum
We propose a multiple-kernel local-patch descriptor based on efficient match kernels from pixel gradients.
no code implementations • 23 Jul 2018 • Ahmet Iscen, Yannis Avrithis, Giorgos Tolias, Teddy Furon, Ondrej Chum
State of the art image retrieval performance is achieved with CNN features and manifold ranking using a k-NN similarity graph that is pre-computed off-line.
1 code implementation • CVPR 2018 • Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondrej Chum
Positive examples are distant points on a single manifold, while negative examples are nearby points on different manifolds.
2 code implementations • CVPR 2018 • Filip Radenović, Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum
In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation for both datasets is created with an extra attention to the reliability of the ground truth.
13 code implementations • 3 Nov 2017 • Filip Radenović, Giorgos Tolias, Ondřej Chum
We show that both hard-positive and hard-negative examples, selected by exploiting the geometry and the camera positions available from the 3D models, enhance the performance of particular-object retrieval.
Ranked #9 on
Image Retrieval
on RParis (Medium)
no code implementations • 14 Sep 2017 • Oriane Siméoni, Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondrej Chum
Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion.
2 code implementations • ECCV 2018 • Filip Radenović, Giorgos Tolias, Ondřej Chum
We cast shape matching as metric learning with convolutional networks.
Ranked #1 on
Sketch-Based Image Retrieval
on Chairs
(using extra training data)
no code implementations • 25 Jul 2017 • Arun Mukundan, Giorgos Tolias, Ondrej Chum
We propose a multiple-kernel local-patch descriptor based on efficient match kernels of patch gradients.
no code implementations • 21 Apr 2017 • Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Teddy Furon, Ondrej Chum
Location recognition is commonly treated as visual instance retrieval on "street view" imagery.
no code implementations • CVPR 2017 • Giorgos Tolias, Ondřej Chum
To demonstrate the advantages of the AFM method, we derive a short vector image representation that, due to asymmetric feature maps, supports efficient scale and translation invariant sketch-based image retrieval.
1 code implementation • CVPR 2018 • Ahmet Iscen, Yannis Avrithis, Giorgos Tolias, Teddy Furon, Ondrej Chum
This makes the Euclidean nearest neighbor search biased for this task.
3 code implementations • CVPR 2017 • Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Teddy Furon, Ondrej Chum
The diffusion is carried out on descriptors of overlapping image regions rather than on a global image descriptor like in previous approaches.
5 code implementations • 8 Apr 2016 • Filip Radenović, Giorgos Tolias, Ondřej Chum
Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks.
Ranked #5 on
Image Retrieval
on Par6k
6 code implementations • 18 Nov 2015 • Giorgos Tolias, Ronan Sicre, Hervé Jégou
Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations.
Ranked #4 on
Image Retrieval
on Par6k
no code implementations • 29 Oct 2014 • Ahmet Iscen, Giorgos Tolias, Philippe-Henri Gosselin, Hervé Jégou
Our results show that the regular dense detector is outperformed by other methods in most situations, leading us to improve the state of the art in comparable setups on standard retrieval and fined-grain benchmarks.
no code implementations • 8 Jul 2014 • Giorgos Tolias, Teddy Furon, Hervé Jégou
Our geometric-aware aggregation strategy is effective for image search, as shown by experiments performed on standard benchmarks for image and particular object retrieval, namely Holidays and Oxford buildings.