Ahmet Iscen | DeepAI

AI Chat

Featured Co-authors

Kai-Wei Chang
160 publications
Cordelia Schmid
156 publications
Yizhou Sun
80 publications
Chen Sun
74 publications
Vincent Gripon
63 publications
Hervé Jégou
59 publications
Boqing Gong
59 publications
Anurag Arnab
35 publications
Ondrej Chum
33 publications
Yannis Avrithis
32 publications
Michael Rabbat
31 publications

∙ 06/13/2023

AVIS: Autonomous Visual Information Seeking with Large Language Models

In this paper, we propose an autonomous information seeking visual quest...

0 Ziniu Hu, et al. ∙

∙ 06/12/2023

Retrieval-Enhanced Contrastive Vision-Text Models

Contrastive image-text models such as CLIP form the building blocks of m...

0 Ahmet Iscen, et al. ∙

∙ 04/11/2023

Improving Image Recognition by Retrieving from Web-Scale Image-Text Data

Retrieval augmented models are becoming increasingly popular for compute...

0 Ahmet Iscen, et al. ∙

∙ 12/10/2022

REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory

In this paper, we propose an end-to-end Retrieval-Augmented Visual Langu...

0 Ziniu Hu, et al. ∙

∙ 10/10/2022

A Memory Transformer Network for Incremental Learning

We study class-incremental learning, a training setup in which new class...

0 Ahmet Iscen, et al. ∙

∙ 02/04/2022

Learning with Neighbor Consistency for Noisy Labels

Recent advances in deep learning have relied on large, labelled datasets...

4 Ahmet Iscen, et al. ∙

∙ 04/12/2021

Class-Balanced Distillation for Long-Tailed Visual Recognition

Real-world imagery is often characterized by a significant imbalance of ...

20 Ahmet Iscen, et al. ∙

∙ 04/01/2020

Memory-Efficient Incremental Learning Through Feature Adaptation

In this work we introduce an approach for incremental learning, which pr...

0 Ahmet Iscen, et al. ∙

∙ 10/01/2019

Graph convolutional networks for learning with few clean and many noisy labels

In this work we consider the problem of learning a classifier from noisy...

42 Ahmet Iscen, et al. ∙

∙ 04/09/2019

Label Propagation for Deep Semi-supervised Learning

Semi-supervised learning is becoming increasingly important because it c...

0 Ahmet Iscen, et al. ∙

∙ 07/25/2018

Local Orthogonal-Group Testing

This work addresses approximate nearest neighbor search applied in the d...

0 Ahmet Iscen, et al. ∙

∙ 07/23/2018

Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking

State of the art image retrieval performance is achieved with CNN featur...

0 Ahmet Iscen, et al. ∙

∙ 03/29/2018

Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking

In this paper we address issues with image retrieval benchmarking on sta...

0 Filip Radenovic, et al. ∙

∙ 03/29/2018

Mining on Manifolds: Metric Learning without Labels

In this work we present a novel unsupervised framework for hard training...

0 Ahmet Iscen, et al. ∙

∙ 09/14/2017

Unsupervised deep object discovery for instance recognition

Severe background clutter is challenging in many computer vision tasks, ...

0 Oriane Siméoni, et al. ∙

∙ 03/20/2017

Fast Spectral Ranking for Similarity Search

Despite the success of deep learning on representing images for particul...

0 Ahmet Iscen, et al. ∙

∙ 11/16/2016

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

Query expansion is a popular method to improve the quality of image retr...

0 Ahmet Iscen, et al. ∙

∙ 12/10/2014

Memory vectors for similarity search in high-dimensional spaces

We study an indexing architecture to store and search in a database of h...

0 Ahmet Iscen, et al. ∙

∙ 10/29/2014

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

We consider a pipeline for image classification or search based on codin...

0 Ahmet Iscen, et al. ∙

∙ 01/03/2014

ConceptVision: A Flexible Scene Classification Framework

We introduce ConceptVision, a method that aims for high accuracy in cate...

0 Ahmet Iscen, et al. ∙

∙ 01/03/2014

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

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

0 Ahmet Iscen, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world