Search Results for author: Ahmet Iscen

Found 18 papers, 7 papers with code

Learning with Neighbor Consistency for Noisy Labels

no code implementations29 Sep 2021 Ahmet Iscen, Jack Valmadre, Anurag Arnab, Cordelia Schmid

However, collecting large datasets in a time- and cost-efficient manner often results in label noise.

Image Classification

Class-Balanced Distillation for Long-Tailed Visual Recognition

3 code implementations12 Apr 2021 Ahmet Iscen, André Araujo, Boqing Gong, Cordelia Schmid

An effective and simple approach to long-tailed visual recognition is to learn feature representations and a classifier separately, with instance and class-balanced sampling, respectively.

Knowledge Distillation Long-tail Learning

Memory-Efficient Incremental Learning Through Feature Adaptation

no code implementations ECCV 2020 Ahmet Iscen, Jeffrey Zhang, Svetlana Lazebnik, Cordelia Schmid

We assume that the model is updated incrementally for new classes as new data becomes available sequentially. This requires adapting the previously stored feature vectors to the updated feature space without having access to the corresponding original training images.

Incremental Learning

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.

Local Orthogonal-Group Testing

no code implementations ECCV 2018 Ahmet Iscen, Ondrej Chum

This work addresses approximate nearest neighbor search applied in the domain of large-scale image retrieval.

Image Retrieval

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

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

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

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.

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

Efficient Large-Scale Similarity Search Using Matrix Factorization

no code implementations CVPR 2016 Ahmet Iscen, Michael Rabbat, Teddy Furon

Experiments with standard image search benchmarks, including the Yahoo100M dataset comprising 100 million images, show that our method gives comparable (and sometimes superior) accuracy compared to exhaustive search while requiring only 10% of the vector operations and memory.

Dictionary Learning Dimensionality Reduction +1

Memory vectors for similarity search in high-dimensional spaces

no code implementations10 Dec 2014 Ahmet Iscen, Teddy Furon, Vincent Gripon, Michael Rabbat, Hervé Jégou

We study an indexing architecture to store and search in a database of high-dimensional vectors from the perspective of statistical signal processing and decision theory.

Image Retrieval

A comparison of dense region detectors for image search and fine-grained classification

no code implementations29 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.

General Classification Image Classification +1

What is usual in unusual videos? Trajectory snippet histograms for discovering unusualness

no code implementations3 Jan 2014 Ahmet Iscen, Anil Armagan, Pinar Duygulu

Unusual events are important as being possible indicators of undesired consequences.

ConceptVision: A Flexible Scene Classification Framework

no code implementations3 Jan 2014 Ahmet Iscen, Eren Golge, Ilker Sarac, Pinar Duygulu

We introduce ConceptVision, a method that aims for high accuracy in categorizing large number of scenes, while keeping the model relatively simpler and efficient for scalability.

General Classification Scene Classification

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