Search Results for author: Yannis Avrithis

Found 31 papers, 15 papers with code

AlignMix: Improving representations by interpolating aligned features

no code implementations29 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.

Data Augmentation Representation Learning

All the attention you need: Global-local, spatial-channel attention for image retrieval

no code implementations16 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.

Image Retrieval Representation Learning

It Takes Two to Tango: Mixup for Deep Metric Learning

no code implementations9 Jun 2021 Shashanka Venkataramanan, Bill Psomas, Yannis Avrithis, Ewa Kijak, Laurent Amsaleg, Konstantinos Karantzalos

To the best of our knowledge, we are the first to investigate mixing examples and target labels for deep metric learning.

 Ranked #1 on Metric Learning on In-Shop (using extra training data)

Data Augmentation Metric Learning +1

Tensor feature hallucination for few-shot learning

1 code implementation9 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.

Data Augmentation Few-Shot Learning +1

Few-shot learning via tensor hallucination

no code implementations19 Apr 2021 Michalis Lazarou, Yannis Avrithis, Tania Stathaki

Few-shot classification addresses the challenge of classifying examples given only limited labeled data.

Data Augmentation Few-Shot Learning +1

AlignMix: Improving representation by interpolating aligned features

no code implementations29 Mar 2021 Shashanka Venkataramanan, Yannis Avrithis, Ewa Kijak, Laurent Amsaleg

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.

Data Augmentation Representation Learning +1

Local Propagation for Few-Shot Learning

no code implementations5 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.

Few-Shot Learning

Iterative label cleaning for transductive and semi-supervised few-shot learning

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.

Few-Shot Learning

Few-Shot Few-Shot Learning and the role of Spatial Attention

no code implementations18 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.

Few-Shot Learning

Walking on the Edge: Fast, Low-Distortion Adversarial Examples

1 code implementation4 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.

Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images

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 #21 on Weakly Supervised Object Detection on PASCAL VOC 2012 test (using extra training data)

Weakly Supervised Object Detection

Rethinking deep active learning: Using unlabeled data at model training

1 code implementation19 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.

Active Learning Image Classification

Local Features and Visual Words Emerge in Activations

1 code implementation15 May 2019 Oriane Siméoni, Yannis Avrithis, Ondrej Chum

We propose a novel method of deep spatial matching (DSM) for image retrieval.

Image Retrieval

Label Propagation for Deep Semi-supervised Learning

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.

Smooth Adversarial Examples

1 code implementation28 Mar 2019 Hanwei Zhang, Yannis Avrithis, Teddy Furon, Laurent Amsaleg

This paper investigates the visual quality of the adversarial examples.

Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking

no code implementations23 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.

Image Retrieval

Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking

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.

Image Retrieval

Mining on Manifolds: Metric Learning without Labels

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.

General Classification Metric Learning

Unsupervised object discovery for instance recognition

no code implementations14 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.

Image Retrieval Object Discovery

Panorama to panorama matching for location recognition

no code implementations21 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.

Unsupervised part learning for visual recognition

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.

General Classification Image Classification +1

Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations

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.

Image Retrieval

Automatic discovery of discriminative parts as a quadratic assignment problem

no code implementations14 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.

General Classification Image Classification

Web-Scale Image Clustering Revisited

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.

Image Clustering Quantization

Early Burst Detection for Memory-Efficient Image Retrieval

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.

Image Retrieval

Locally Optimized Product Quantization for Approximate Nearest Neighbor Search

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.

Quantization

Cannot find the paper you are looking for? You can Submit a new open access paper.