Björn Barz

is this you? claim profile

0 followers
Friedrich-Schiller-Universität Jena

Content-based Image Retrieval and the Semantic Gap in the Deep Learning Era

Content-based image retrieval has seen astonishing progress over the pas...
11/12/2020 ∙ by Björn Barz, et al. ∙ 0 ∙ share

read it
Finding Relevant Flood Images on Twitter using Content-based Filters

The analysis of natural disasters such as floods in a timely manner ofte...
11/11/2020 ∙ by Björn Barz, et al. ∙ 0 ∙ share

read it
Making Every Label Count: Handling Semantic Imprecision by Integrating Domain Knowledge

Noisy data, crawled from the web or supplied by volunteers such as Mecha...
10/13/2020 ∙ by Clemens-Alexander Brust, et al. ∙ 0 ∙ share

read it
Enhancing Flood Impact Analysis using Interactive Retrieval of Social Media Images

The analysis of natural disasters such as floods in a timely manner ofte...
08/09/2019 ∙ by Björn Barz, et al. ∙ 0 ∙ share

read it
Do we train on test data? Purging CIFAR of near-duplicates

We find that 3.3 sets, respectively, have duplicates in the training set...
02/01/2019 ∙ by Björn Barz, et al. ∙ 0 ∙ share

read it
Deep Learning on Small Datasets without Pre-Training using Cosine Loss

Two things seem to be indisputable in the contemporary deep learning dis...
01/25/2019 ∙ by Björn Barz, et al. ∙ 0 ∙ share

read it
Towards Automatic Identification of Elephants in the Wild

Identifying animals from a large group of possible individuals is very i...
12/11/2018 ∙ by Matthias Körschens, et al. ∙ 0 ∙ share

read it
Hierarchy-based Image Embeddings for Semantic Image Retrieval

Deep neural networks trained for classification have been found to learn...
09/26/2018 ∙ by Björn Barz, et al. ∙ 2 ∙ share

read it
Information-Theoretic Active Learning for Content-Based Image Retrieval

We propose Information-Theoretic Active Learning (ITAL), a novel batch-m...
09/07/2018 ∙ by Björn Barz, et al. ∙ 6 ∙ share

read it
Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detection

Automatic detection of anomalies in space- and time-varying measurements...
04/19/2018 ∙ by Björn Barz, et al. ∙ 0 ∙ share

read it
Automatic Query Image Disambiguation for Content-Based Image Retrieval

Query images presented to content-based image retrieval systems often ha...
11/02/2017 ∙ by Björn Barz, et al. ∙ 0 ∙ share

read it
Fast Learning and Prediction for Object Detection using Whitened CNN Features

We combine features extracted from pre-trained convolutional neural netw...
04/10/2017 ∙ by Björn Barz, et al. ∙ 0 ∙ share

read it
Maximally Divergent Intervals for Anomaly Detection

We present new methods for batch anomaly detection in multivariate time ...
10/21/2016 ∙ by Erik Rodner, et al. ∙ 0 ∙ share

read it
ARTOS -- Adaptive Real-Time Object Detection System

ARTOS is all about creating, tuning, and applying object detection model...
07/10/2014 ∙ by Björn Barz, et al. ∙ 0 ∙ share

read it

Björn Barz

Featured Co-authors

Bin Yang

Joachim Denzler

Erik Rodner

Clemens-Alexander Brust

Markus Reichstein

Christoph Käding

Paul Bodesheim

Kai Schröter

Miguel Mahecha

Ann-Christin Kra

Matthias Körschens

Content-based Image Retrieval and the Semantic Gap in the Deep Learning Era

Finding Relevant Flood Images on Twitter using Content-based Filters

Making Every Label Count: Handling Semantic Imprecision by Integrating Domain Knowledge

Enhancing Flood Impact Analysis using Interactive Retrieval of Social Media Images

Do we train on test data? Purging CIFAR of near-duplicates

Deep Learning on Small Datasets without Pre-Training using Cosine Loss

Towards Automatic Identification of Elephants in the Wild

Hierarchy-based Image Embeddings for Semantic Image Retrieval

Information-Theoretic Active Learning for Content-Based Image Retrieval

Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detection

Automatic Query Image Disambiguation for Content-Based Image Retrieval

Fast Learning and Prediction for Object Detection using Whitened CNN Features

Maximally Divergent Intervals for Anomaly Detection

ARTOS -- Adaptive Real-Time Object Detection System