Search Results for author: Joachim Denzler

Found 61 papers, 16 papers with code

Data-Driven Detection of General Chiasmi Using Lexical and Semantic Features

no code implementations EMNLP (LaTeCHCLfL, CLFL, LaTeCH) 2021 Felix Schneider, Björn Barz, Phillip Brandes, Sophie Marshall, Joachim Denzler

In contrast, we propose an approach targeting the more general and challenging case A B B’ A’, where the words A, A’ and B, B’ constituting the chiasmus do not need to be identical but just related in meaning.

Argument Mining Word Embeddings

Determining the Relevance of Features for Deep Neural Networks

no code implementations ECCV 2020 Christian Reimers, Jakob Runge, Joachim Denzler

Deep neural networks are tremendously successful in many applications, but end-to-end trained networks often result in hard to understand black-box classifiers or predictors.

Causal Inference

Domain Adaptation and Active Learning for Fine-Grained Recognition in the Field of Biodiversity

no code implementations22 Oct 2021 Bernd Gruner, Matthias Körschens, Björn Barz, Joachim Denzler

We discovered that domain adaptation works very well for fine-grained recognition and that the normalization methods have a great influence on the results.

Active Learning Transfer Learning +1

A Strong Baseline for the VIPriors Data-Efficient Image Classification Challenge

no code implementations28 Sep 2021 Björn Barz, Lorenzo Brigato, Luca Iocchi, Joachim Denzler

Learning from limited amounts of data is the hallmark of intelligence, requiring strong generalization and abstraction skills.

Classification Image Classification

Causal Inference in Non-linear Time-series using Deep Networks and Knockoff Counterfactuals

no code implementations22 Sep 2021 Wasim Ahmad, Maha Shadaydeh, Joachim Denzler

Overall our method outperforms the widely used vector autoregressive Granger causality and PCMCI in detecting nonlinear causal dependency in multivariate time series.

Causal Inference Time Series

Anomaly Attribution of Multivariate Time Series using Counterfactual Reasoning

no code implementations14 Sep 2021 Violeta Teodora Trifunov, Maha Shadaydeh, Björn Barz, Joachim Denzler

There are numerous methods for detecting anomalies in time series, but that is only the first step to understanding them.

Time Series

Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification

1 code implementation30 Aug 2021 Lorenzo Brigato, Björn Barz, Luca Iocchi, Joachim Denzler

Data-efficient image classification using deep neural networks in settings, where only small amounts of labeled data are available, has been an active research area in the recent past.

Small Data Image Classification

WikiChurches: A Fine-Grained Dataset of Architectural Styles with Real-World Challenges

no code implementations16 Aug 2021 Björn Barz, Joachim Denzler

We introduce a novel dataset for architectural style classification, consisting of 9, 485 images of church buildings.

Self-Supervised Learning from Semantically Imprecise Data

no code implementations22 Apr 2021 Clemens-Alexander Brust, Björn Barz, Joachim Denzler

CHILLAX, a recently proposed method to tackle this task, leverages a hierarchical classifier to learn from imprecise labels.

Self-Supervised Learning

Towards Learning an Unbiased Classifier from Biased Data via Conditional Adversarial Debiasing

no code implementations10 Mar 2021 Christian Reimers, Paul Bodesheim, Jakob Runge, Joachim Denzler

Often, the bias of a classifier is a direct consequence of a bias in the training dataset, frequently caused by the co-occurrence of relevant features and irrelevant ones.

Counterfactual Generation with Knockoffs

no code implementations1 Feb 2021 Oana-Iuliana Popescu, Maha Shadaydeh, Joachim Denzler

Heuristic methods result in false-positive artifacts because the image after the perturbation is far from the original data distribution.

Variable Selection

Analysing the Direction of Emotional Influence in Nonverbal Dyadic Communication: A Facial-Expression Study

no code implementations16 Dec 2020 Maha Shadaydeh, Lea Mueller, Dana Schneider, Martin Thuemmel, Thomas Kessler, Joachim Denzler

Identifying the direction of emotional influence in a dyadic dialogue is of increasing interest in the psychological sciences with applications in psychotherapy, analysis of political interactions, or interpersonal conflict behavior.

Causal Inference Time Series

EarthNet2021: A novel large-scale dataset and challenge for forecasting localized climate impacts

1 code implementation11 Dec 2020 Christian Requena-Mesa, Vitus Benson, Joachim Denzler, Jakob Runge, Markus Reichstein

Here, we define high-resolution Earth surface forecasting as video prediction of satellite imagery conditional on mesoscale weather forecasts.

Crop Yield Prediction Earth Surface Forecasting

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

no code implementations12 Nov 2020 Björn Barz, Joachim Denzler

Content-based image retrieval has seen astonishing progress over the past decade, especially for the task of retrieving images of the same object that is depicted in the query image.

Content-Based Image Retrieval

Finding Relevant Flood Images on Twitter using Content-based Filters

1 code implementation11 Nov 2020 Björn Barz, Kai Schröter, Ann-Christin Kra, Joachim Denzler

The analysis of natural disasters such as floods in a timely manner often suffers from limited data due to coarsely distributed sensors or sensor failures.

End-to-end Learning of a Fisher Vector Encoding for Part Features in Fine-grained Recognition

no code implementations4 Jul 2020 Dimitri Korsch, Paul Bodesheim, Joachim Denzler

We assume that part-based methods suffer from a missing representation of local features, which is invariant to the order of parts and can handle a varying number of visible parts appropriately.

Fine-Grained Image Classification

Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detection

1 code implementation14 Jun 2020 Nils Gählert, Nicolas Jourdan, Marius Cordts, Uwe Franke, Joachim Denzler

In addition, we complement the Cityscapes benchmark suite with 3D vehicle detection based on the new annotations as well as metrics presented in this work.

Autonomous Driving

Active and Incremental Learning with Weak Supervision

no code implementations20 Jan 2020 Clemens-Alexander Brust, Christoph Käding, Joachim Denzler

By selecting unlabeled examples that are promising in terms of model improvement and only asking for respective labels, active learning can increase the efficiency of the labeling process in terms of time and cost.

Active Learning Incremental Learning +1

LOST: A flexible framework for semi-automatic image annotation

2 code implementations16 Oct 2019 Jonas Jäger, Gereon Reus, Joachim Denzler, Viviane Wolff, Klaus Fricke-Neuderth

In this paper we present a framework that allows for a quick and flexible design of semi-automatic annotation pipelines.

Facial Behavior Analysis using 4D Curvature Statistics for Presentation Attack Detection

no code implementations14 Oct 2019 Martin Thümmel, Sven Sickert, Joachim Denzler

As a countermeasure, we propose a method that automatically analyzes the plausibility of facial behavior based on a sequence of 3D face scans.

Anomaly Detection

Predicting Landscapes from Environmental Conditions Using Generative Networks

no code implementations23 Sep 2019 Christian Requena-Mesa, Markus Reichstein, Miguel Mahecha, Basil Kraft, Joachim Denzler

We demonstrate that for many purposes the generated landscapes behave as real with immediate application for global change studies.

Classification-Specific Parts for Improving Fine-Grained Visual Categorization

1 code implementation16 Sep 2019 Dimitri Korsch, Paul Bodesheim, Joachim Denzler

Fine-grained visual categorization is a classification task for distinguishing categories with high intra-class and small inter-class variance.

Ranked #4 on Fine-Grained Image Classification on NABirds (using extra training data)

Classification Feature Importance +3

Self-supervised Data Bootstrapping for Deep Optical Character Recognition of Identity Documents

no code implementations12 Aug 2019 Oliver Mothes, Joachim Denzler

In combination with synthetically generated character data, the real data is used to train efficient convolutional neural networks for character classification serving a practical runtime as well as a high accuracy.

Optical Character Recognition

Enhancing Flood Impact Analysis using Interactive Retrieval of Social Media Images

1 code implementation9 Aug 2019 Björn Barz, Kai Schröter, Moritz Münch, Bin Yang, Andrea Unger, Doris Dransch, Joachim Denzler

The analysis of natural disasters such as floods in a timely manner often suffers from limited data due to a coarse distribution of sensors or sensor failures.

Content-Based Image Retrieval

Do We Train on Test Data? Purging CIFAR of Near-Duplicates

no code implementations1 Feb 2019 Björn Barz, Joachim Denzler

However, we find that 3. 3% and 10% of the images from the test sets of these datasets have duplicates in the training set.

General Classification

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

1 code implementation25 Jan 2019 Björn Barz, Joachim Denzler

The categorical cross-entropy loss after softmax activation is the method of choice for classification.

Classification General Classification

Towards Automatic Identification of Elephants in the Wild

no code implementations11 Dec 2018 Matthias Körschens, Björn Barz, Joachim Denzler

Identifying animals from a large group of possible individuals is very important for biodiversity monitoring and especially for collecting data on a small number of particularly interesting individuals, as these have to be identified first before this can be done.

Not just a matter of semantics: the relationship between visual similarity and semantic similarity

no code implementations17 Nov 2018 Clemens-Alexander Brust, Joachim Denzler

In this paper, we use five different semantic and visual similarity measures each to thoroughly analyze the relationship without relying too much on any single definition.

Image Retrieval Semantic Similarity +3

Integrating domain knowledge: using hierarchies to improve deep classifiers

no code implementations17 Nov 2018 Clemens-Alexander Brust, Joachim Denzler

In this paper, we propose to make use of preexisting class hierarchies like WordNet to integrate additional domain knowledge into classification.

Data Augmentation General Classification

Hierarchy-based Image Embeddings for Semantic Image Retrieval

1 code implementation26 Sep 2018 Björn Barz, Joachim Denzler

Such an embedding does not only improve image retrieval results, but could also facilitate integrating semantics for other tasks, e. g., novelty detection or few-shot learning.

Few-Shot Learning Image Retrieval +2

Active Learning for Deep Object Detection

no code implementations26 Sep 2018 Clemens-Alexander Brust, Christoph Käding, Joachim Denzler

In this paper, we combine a novel method of active learning for object detection with an incremental learning scheme to enable continuous exploration of new unlabeled datasets.

Active Learning Incremental Learning +1

Information-Theoretic Active Learning for Content-Based Image Retrieval

1 code implementation7 Sep 2018 Björn Barz, Christoph Käding, Joachim Denzler

We propose Information-Theoretic Active Learning (ITAL), a novel batch-mode active learning method for binary classification, and apply it for acquiring meaningful user feedback in the context of content-based image retrieval.

Active Learning Content-Based Image Retrieval

Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detection

1 code implementation19 Apr 2018 Björn Barz, Erik Rodner, Yanira Guanche Garcia, Joachim Denzler

Automatic detection of anomalies in space- and time-varying measurements is an important tool in several fields, e. g., fraud detection, climate analysis, or healthcare monitoring.

Anomaly Detection Fraud Detection +1

Automatic Query Image Disambiguation for Content-Based Image Retrieval

1 code implementation2 Nov 2017 Björn Barz, Joachim Denzler

Query images presented to content-based image retrieval systems often have various different interpretations, making it difficult to identify the search objective pursued by the user.

Content-Based Image Retrieval

Her2 Challenge Contest: A Detailed Assessment of Automated Her2 Scoring Algorithms in Whole Slide Images of Breast Cancer Tissues

no code implementations23 May 2017 Talha Qaiser, Abhik Mukherjee, Chaitanya Reddy Pb, Sai Dileep Munugoti, Vamsi Tallam, Tomi Pitkäaho, Taina Lehtimäki, Thomas Naughton, Matt Berseth, Aníbal Pedraza, Ramakrishnan Mukundan, Matthew Smith, Abhir Bhalerao, Erik Rodner, Marcel Simon, Joachim Denzler, Chao-Hui Huang, Gloria Bueno, David Snead, Ian Ellis, Mohammad Ilyas, Nasir Rajpoot

In this paper, we report on a recent automated Her2 scoring contest, held in conjunction with the annual PathSoc meeting held in Nottingham in June 2016, aimed at systematically comparing and advancing the state-of-the-art Artificial Intelligence (AI) based automated methods for Her2 scoring.

whole slide images

Generalized orderless pooling performs implicit salient matching

2 code implementations ICCV 2017 Marcel Simon, Yang Gao, Trevor Darrell, Joachim Denzler, Erik Rodner

In this paper, we generalize average and bilinear pooling to "alpha-pooling", allowing for learning the pooling strategy during training.

Fast Learning and Prediction for Object Detection using Whitened CNN Features

no code implementations10 Apr 2017 Björn Barz, Erik Rodner, Christoph Käding, Joachim Denzler

We combine features extracted from pre-trained convolutional neural networks (CNNs) with the fast, linear Exemplar-LDA classifier to get the advantages of both: the high detection performance of CNNs, automatic feature engineering, fast model learning from few training samples and efficient sliding-window detection.

Feature Engineering Real-Time Object Detection +1

Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changes

no code implementations19 Dec 2016 Christoph Käding, Erik Rodner, Alexander Freytag, Joachim Denzler

The demands on visual recognition systems do not end with the complexity offered by current large-scale image datasets, such as ImageNet.

Active Learning

ImageNet pre-trained models with batch normalization

3 code implementations5 Dec 2016 Marcel Simon, Erik Rodner, Joachim Denzler

Convolutional neural networks (CNN) pre-trained on ImageNet are the backbone of most state-of-the-art approaches.

Fine-grained Recognition in the Noisy Wild: Sensitivity Analysis of Convolutional Neural Networks Approaches

no code implementations21 Oct 2016 Erik Rodner, Marcel Simon, Robert B. Fisher, Joachim Denzler

In this paper, we study the sensitivity of CNN outputs with respect to image transformations and noise in the area of fine-grained recognition.

Impatient DNNs - Deep Neural Networks with Dynamic Time Budgets

no code implementations10 Oct 2016 Manuel Amthor, Erik Rodner, Joachim Denzler

We propose Impatient Deep Neural Networks (DNNs) which deal with dynamic time budgets during application.

Color: A Crucial Factor for Aesthetic Quality Assessment in a Subjective Dataset of Paintings

no code implementations19 Sep 2016 Seyed Ali Amirshahi, Gregor Uwe Hayn-Leichsenring, Joachim Denzler, Christoph Redies

As a first step and to assess this dataset, using a classifier, we investigate the correlation between the subjective scores and two widely used features that are related to color perception and in different aesthetic quality assessment approaches.

General Classification

Neither Quick Nor Proper -- Evaluation of QuickProp for Learning Deep Neural Networks

no code implementations14 Jun 2016 Clemens-Alexander Brust, Sven Sickert, Marcel Simon, Erik Rodner, Joachim Denzler

Neural networks and especially convolutional neural networks are of great interest in current computer vision research.

Semantic Segmentation

Fine-grained Recognition Datasets for Biodiversity Analysis

no code implementations3 Jul 2015 Erik Rodner, Marcel Simon, Gunnar Brehm, Stephanie Pietsch, J. Wolfgang Wägele, Joachim Denzler

In the following paper, we present and discuss challenging applications for fine-grained visual classification (FGVC): biodiversity and species analysis.

Classification Fine-Grained Image Classification +1

Active Learning and Discovery of Object Categories in the Presence of Unnameable Instances

no code implementations CVPR 2015 Christoph Kading, Alexander Freytag, Erik Rodner, Paul Bodesheim, Joachim Denzler

In active learning, all categories occurring in collected data are usually assumed to be known in advance and experts should be able to label every requested instance.

Active Learning

Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding

no code implementations23 Feb 2015 Clemens-Alexander Brust, Sven Sickert, Marcel Simon, Erik Rodner, Joachim Denzler

Classifying single image patches is important in many different applications, such as road detection or scene understanding.

Scene Understanding

Part Detector Discovery in Deep Convolutional Neural Networks

1 code implementation12 Nov 2014 Marcel Simon, Erik Rodner, Joachim Denzler

Current fine-grained classification approaches often rely on a robust localization of object parts to extract localized feature representations suitable for discrimination.

General Classification

ARTOS -- Adaptive Real-Time Object Detection System

no code implementations10 Jul 2014 Björn Barz, Erik Rodner, Joachim Denzler

ARTOS is all about creating, tuning, and applying object detection models with just a few clicks.

Real-Time Object Detection

Instance-weighted Transfer Learning of Active Appearance Models

no code implementations CVPR 2014 Daniel Haase, Erik Rodner, Joachim Denzler

Therefore, we present a transfer learning method that is able to learn from related training data using an instance-weighted transfer technique.

Transfer Learning

Fine-grained Categorization -- Short Summary of our Entry for the ImageNet Challenge 2012

no code implementations17 Oct 2013 Christoph Göring, Alexander Freytag, Erik Rodner, Joachim Denzler

In this paper, we tackle the problem of visual categorization of dog breeds, which is a surprisingly challenging task due to simultaneously present low interclass distances and high intra-class variances.

Kernel Null Space Methods for Novelty Detection

no code implementations CVPR 2013 Paul Bodesheim, Alexander Freytag, Erik Rodner, Michael Kemmler, Joachim Denzler

In contrast to modeling the support of each known class individually, our approach makes use of a projection in a joint subspace where training samples of all known classes have zero intra-class variance.

Density Estimation Object Recognition

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