Search Results for author: Ismail Elezi

Found 24 papers, 13 papers with code

Revealing Structure in Large Graphs: Szemerédi's Regularity Lemma and its Use in Pattern Recognition

no code implementations21 Sep 2016 Marcello Pelillo, Ismail Elezi, Marco Fiorucci

Introduced in the mid-1970's as an intermediate step in proving a long-standing conjecture on arithmetic progressions, Szemer\'edi's regularity lemma has emerged over time as a fundamental tool in different branches of graph theory, combinatorics and theoretical computer science.

LEMMA

DeepScores -- A Dataset for Segmentation, Detection and Classification of Tiny Objects

2 code implementations27 Mar 2018 Lukas Tuggener, Ismail Elezi, Jürgen Schmidhuber, Marcello Pelillo, Thilo Stadelmann

We present the DeepScores dataset with the goal of advancing the state-of-the-art in small objects recognition, and by placing the question of object recognition in the context of scene understanding.

General Classification Object +3

Transductive Label Augmentation for Improved Deep Network Learning

no code implementations26 May 2018 Ismail Elezi, Alessandro Torcinovich, Sebastiano Vascon, Marcello Pelillo

Motivated by the observation that in virtually all application domains it is easy to obtain unlabeled data, in this paper we take a different perspective and propose a \emph{label augmentation} approach.

Data Augmentation General Classification +2

Deep Watershed Detector for Music Object Recognition

no code implementations26 May 2018 Lukas Tuggener, Ismail Elezi, Jurgen Schmidhuber, Thilo Stadelmann

Optical Music Recognition (OMR) is an important and challenging area within music information retrieval, the accurate detection of music symbols in digital images is a core functionality of any OMR pipeline.

Information Retrieval Music Information Retrieval +6

Learning Neural Models for End-to-End Clustering

1 code implementation11 Jul 2018 Benjamin Bruno Meier, Ismail Elezi, Mohammadreza Amirian, Oliver Durr, Thilo Stadelmann

We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass.

Clustering Metric Learning

Deep Learning in the Wild

no code implementations13 Jul 2018 Thilo Stadelmann, Mohammadreza Amirian, Ismail Arabaci, Marek Arnold, Gilbert François Duivesteijn, Ismail Elezi, Melanie Geiger, Stefan Lörwald, Benjamin Bruno Meier, Katharina Rombach, Lukas Tuggener

Deep learning with neural networks is applied by an increasing number of people outside of classic research environments, due to the vast success of the methodology on a wide range of machine perception tasks.

The Group Loss for Deep Metric Learning

2 code implementations ECCV 2020 Ismail Elezi, Sebastiano Vascon, Alessandro Torcinovich, Marcello Pelillo, Laura Leal-Taixe

Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes.

Ranked #20 on Metric Learning on CUB-200-2011 (using extra training data)

Clustering Image Retrieval +2

CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks

1 code implementation CVPR 2020 Maxim Maximov, Ismail Elezi, Laura Leal-Taixé

In many real-world scenarios like people tracking or action recognition, it is important to be able to process the data while taking careful consideration in protecting people's identity.

Action Recognition De-identification +1

Exploiting Contextual Information with Deep Neural Networks

no code implementations21 Jun 2020 Ismail Elezi

In this thesis, we show that contextual information can be exploited in 2 fundamentally different ways: implicitly and explicitly.

Deep Active Learning for Object Detection with Mixture Density Networks

no code implementations1 Jan 2021 Jiwoong Choi, Ismail Elezi, Hyuk-Jae Lee, Clement Farabet, Jose M. Alvarez

For active learning, we propose a scoring function that aggregates uncertainties from both the classification and the localization outputs of the network.

Active Learning Informativeness +3

Learning Intra-Batch Connections for Deep Metric Learning

2 code implementations15 Feb 2021 Jenny Seidenschwarz, Ismail Elezi, Laura Leal-Taixé

To this end, we propose an approach based on message passing networks that takes all the relations in a mini-batch into account.

Clustering Image Retrieval +2

Active Learning for Deep Object Detection via Probabilistic Modeling

1 code implementation ICCV 2021 Jiwoong Choi, Ismail Elezi, Hyuk-Jae Lee, Clement Farabet, Jose M. Alvarez

Most of these methods are based on multiple models or are straightforward extensions of classification methods, hence estimate an image's informativeness using only the classification head.

Active Learning Classification +5

The Group Loss++: A deeper look into group loss for deep metric learning

no code implementations4 Apr 2022 Ismail Elezi, Jenny Seidenschwarz, Laurin Wagner, Sebastiano Vascon, Alessandro Torcinovich, Marcello Pelillo, Laura Leal-Taixe

Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes.

Clustering Image Retrieval +3

Learning to Discover and Detect Objects

1 code implementation19 Oct 2022 Vladimir Fomenko, Ismail Elezi, Deva Ramanan, Laura Leal-Taixé, Aljoša Ošep

We then train our network to learn to classify each RoI, either as one of the known classes, seen in the source dataset, or one of the novel classes, with a long-tail distribution constraint on the class assignments, reflecting the natural frequency of classes in the real world.

Novel Class Discovery Novel Object Detection +3

G3DR: Generative 3D Reconstruction in ImageNet

1 code implementation1 Mar 2024 Pradyumna Reddy, Ismail Elezi, Jiankang Deng

We introduce a novel 3D generative method, Generative 3D Reconstruction (G3DR) in ImageNet, capable of generating diverse and high-quality 3D objects from single images, addressing the limitations of existing methods.

3D Reconstruction

Deep Active Learning: A Reality Check

no code implementations21 Mar 2024 Edrina Gashi, Jiankang Deng, Ismail Elezi

By uncovering the limitations of current methods and understanding the impact of different experimental settings, we aim to inspire more efficient training of deep learning models in real-world scenarios with limited annotation budgets.

Active Learning object-detection +1

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