1 code implementation • 24 May 2024 • Bill Psomas, Ioannis Kakogeorgiou, Nikos Efthymiadis, Giorgos Tolias, Ondrej Chum, Yannis Avrithis, Konstantinos Karantzalos
Various attributes can be modified by the textual part, such as shape, color, or context.
Ranked #1 on Composed Image Retrieval (CoIR) on PatternCom
1 code implementation • 10 May 2024 • Yonghao Xu, Pedram Ghamisi, Yannis Avrithis
Multi-target unsupervised domain adaptation (UDA) aims to learn a unified model to address the domain shift between multiple target domains.
no code implementations • 23 Apr 2024 • Felipe Torres, Hanwei Zhang, Ronan Sicre, Stéphane Ayache, Yannis Avrithis
Explanations obtained from transformer-based architectures in the form of raw attention, can be seen as a class-agnostic saliency map.
no code implementations • 23 Apr 2024 • Felipe Torres Figueroa, Hanwei Zhang, Ronan Sicre, Yannis Avrithis, Stephane Ayache
This paper studies interpretability of convolutional networks by means of saliency maps.
1 code implementation • 1 Apr 2024 • Chull Hwan Song, Jooyoung Yoon, Taebaek Hwang, Shunghyun Choi, Yeong Hyeon Gu, Yannis Avrithis
How important is it for training and evaluation sets to not have class overlap in image retrieval?
no code implementations • 19 Dec 2023 • Efthymios Georgiou, Yannis Avrithis, Alexandros Potamianos
Multimodal sentiment analysis (MSA) leverages heterogeneous data sources to interpret the complex nature of human sentiments.
1 code implementation • 30 Oct 2023 • Michalis Lazarou, Yannis Avrithis, Guangyu Ren, Tania Stathaki
Our novel algorithm, Adaptive Anchor Label Propagation}, outperforms the standard label propagation algorithm by as much as 7% and 2% in the 1-shot and 5-shot settings respectively.
no code implementations • 12 Oct 2023 • Shashanka Venkataramanan, Mamshad Nayeem Rizve, João Carreira, Yuki M. Asano, Yannis Avrithis
But are we making the best use of data?
1 code implementation • 27 Sep 2023 • Deniz Engin, Yannis Avrithis
Recent vision-language models are driven by large-scale pretrained models.
Few-shot Video Question Answering Zero-Shot Video Question Answer
1 code implementation • ICCV 2023 • Bill Psomas, Ioannis Kakogeorgiou, Konstantinos Karantzalos, Yannis Avrithis
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.
no code implementations • 27 Apr 2023 • Michalis Lazarou, Yannis Avrithis, Tania Stathaki
Our method exploits the underlying manifold of the labeled support examples and unlabeled queries by using manifold similarity to predict the class probability distribution per query.
no code implementations • 16 Mar 2023 • Konstantinos Tertikas, Despoina Paschalidou, Boxiao Pan, Jeong Joon Park, Mikaela Angelina Uy, Ioannis Emiris, Yannis Avrithis, Leonidas Guibas
Evaluations on various ShapeNet categories demonstrate the ability of our model to generate editable 3D objects of improved fidelity, compared to previous part-based generative approaches that require 3D supervision or models relying on NeRFs.
no code implementations • 17 Jan 2023 • Hanwei Zhang, Felipe Torres, Ronan Sicre, Yannis Avrithis, Stephane Ayache
Methods based on class activation maps (CAM) provide a simple mechanism to interpret predictions of convolutional neural networks by using linear combinations of feature maps as saliency maps.
1 code implementation • CVPR 2023 • Konstantinos Tertikas, Despoina Paschalidou, Boxiao Pan, Jeong Joon Park, Mikaela Angelina Uy, Ioannis Emiris, Yannis Avrithis, Leonidas Guibas
Evaluations on various ShapeNet categories demonstrate the ability of our model to generate editable 3D objects of improved fidelity, compared to previous part-based generative approaches that require 3D supervision or models relying on NeRFs.
1 code implementation • 21 Oct 2022 • Chull Hwan Song, Jooyoung Yoon, Shunghyun Choi, Yannis Avrithis
(4) We enhance locality of interactions at the deeper layers of the encoder, which is the relative weakness of vision transformers.
no code implementations • 29 Jun 2022 • Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg, Yannis Avrithis
Finally, to address inconsistencies due to linear target interpolation, we introduce a self-distillation approach to generate and interpolate synthetic targets.
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.
no code implementations • 29 Sep 2021 • Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg, Yannis Avrithis
Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels.
no code implementations • 16 Jul 2021 • Chull Hwan Song, Hye Joo Han, Yannis Avrithis
Apart from backbone, training pipelines and loss functions, popular approaches have focused on different spatial pooling and attention mechanisms, which are at the core of learning a powerful global image representation.
1 code implementation • ICLR 2022 • Shashanka Venkataramanan, Bill Psomas, Ewa Kijak, Laurent Amsaleg, Konstantinos Karantzalos, Yannis Avrithis
In this work, we aim to bridge this gap and improve representations using mixup, which is a powerful data augmentation approach interpolating two or more examples and corresponding target labels at a time.
Ranked #8 on Metric Learning on CUB-200-2011 (using extra training data)
1 code implementation • 9 Jun 2021 • Michalis Lazarou, Tania Stathaki, Yannis Avrithis
We follow a different approach and investigate how a simple and straightforward synthetic data generation method can be used effectively.
1 code implementation • 19 Apr 2021 • Michalis Lazarou, Yannis Avrithis, Tania Stathaki
Few-shot classification addresses the challenge of classifying examples given only limited labeled data.
2 code implementations • CVPR 2022 • Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg, Yannis Avrithis
Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels.
Ranked #1 on Representation Learning on CIFAR10
1 code implementation • ICCV 2021 • Deniz Engin, François Schnitzler, Ngoc Q. K. Duong, Yannis Avrithis
High-level understanding of stories in video such as movies and TV shows from raw data is extremely challenging.
Ranked #1 on Video Question Answering on KnowIT VQA
no code implementations • 5 Jan 2021 • Yann Lifchitz, Yannis Avrithis, Sylvaine Picard
The challenge in few-shot learning is that available data is not enough to capture the underlying distribution.
1 code implementation • ICCV 2021 • Michalis Lazarou, Tania Stathaki, Yannis Avrithis
Few-shot learning amounts to learning representations and acquiring knowledge such that novel tasks may be solved with both supervision and data being limited.
2 code implementations • CVPR 2021 • Mateusz Budnik, Yannis Avrithis
This acts as a simple combination of knowledge transfer with the original metric learning task.
no code implementations • 18 Feb 2020 • Yann Lifchitz, Yannis Avrithis, Sylvaine Picard
This motivates us to study a problem where the representation is obtained from a classifier pre-trained on a large-scale dataset of a different domain, assuming no access to its training process, while the base class data are limited to few examples per class and their role is to adapt the representation to the domain at hand rather than learn from scratch.
1 code implementation • 4 Dec 2019 • Hanwei Zhang, Yannis Avrithis, Teddy Furon, Laurent Amsaleg
Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input.
no code implementations • arXiv 2019 • Zhaohui Yang, Miaojing Shi, Chao Xu, Vittorio Ferrari, Yannis Avrithis
Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set.
Ranked #23 on Weakly Supervised Object Detection on PASCAL VOC 2012 test (using extra training data)
1 code implementation • 19 Nov 2019 • Oriane Siméoni, Mateusz Budnik, Yannis Avrithis, Guillaume Gravier
By systematically evaluating on a number of popular acquisition strategies and datasets, we find that the use of unlabeled data during model training brings a surprising accuracy improvement in image classification, compared to the differences between acquisition strategies.
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 • 15 May 2019 • Oriane Siméoni, Yannis Avrithis, Ondrej Chum
We propose a novel method of deep spatial matching (DSM) for image retrieval.
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.
1 code implementation • 28 Mar 2019 • Hanwei Zhang, Yannis Avrithis, Teddy Furon, Laurent Amsaleg
This paper investigates the visual quality of the adversarial examples.
no code implementations • CVPR 2019 • Yann Lifchitz, Yannis Avrithis, Sylvaine Picard, Andrei Bursuc
Training deep neural networks from few examples is a highly challenging and key problem for many computer vision tasks.
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.
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.
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 • Ronan Sicre, Yannis Avrithis, Ewa Kijak, Frederic Jurie
This strategy opens the door to the use of PBM in new applications for which the notion of image categories is irrelevant, such as instance-based image retrieval, for example.
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.
no code implementations • 14 Nov 2016 • Ronan Sicre, Julien Rabin, Yannis Avrithis, Teddy Furon, Frederic Jurie
Part-based image classification consists in representing categories by small sets of discriminative parts upon which a representation of the images is built.
1 code implementation • ICCV 2015 • Yannis Avrithis, Yannis Kalantidis, Evangelos Anagnostopoulos, Ioannis Z. Emiris
Large scale duplicate detection, clustering and mining of documents or images has been conventionally treated with seed detection via hashing, followed by seed growing heuristics using fast search.
no code implementations • CVPR 2015 • Miaojing Shi, Yannis Avrithis, Herve Jegou
Then, we show the interest of using this strategy in an asymmetrical manner, with only the database features being aggregated but not those of the query.
no code implementations • CVPR 2014 • Yannis Kalantidis, Yannis Avrithis
We present a simple vector quantizer that combines low distortion with fast search and apply it to approximate nearest neighbor (ANN) search in high dimensional spaces.