Search Results for author:
Found 76 papers, 23 papers with code
Metaphor Detection for Low Resource Languages: From Zero-Shot to Few-Shot Learning in Middle High German
We train this method in a zero-shot pseudo-supervised manner by generating artificial metaphor examples and show that our approach can be used to generate a metaphor dataset with low annotation cost.
Data-Driven Detection of General Chiasmi Using Lexical and Semantic Features
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.
Determining the Relevance of Features for Deep Neural Networks
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.
The Power of Properties: Uncovering the Influential Factors in Emotion Classification
We introduce a workflow to evaluate explicit properties and their impact.
Embracing the black box: Heading towards foundation models for causal discovery from time series data
Our empirical findings suggest that causal discovery in a supervised manner is possible, assuming that the training and test time series samples share most of their dynamics.
JeFaPaTo -- A joint toolbox for blinking analysis and facial features extraction
One area of interest is the subtle movements involved in blinking, a process that is not yet fully understood and needs high-resolution, time-specific analysis for detailed understanding.
Privacy-Preserving Face Recognition in Hybrid Frequency-Color Domain
Lastly, secure multiparty computation is implemented for safely computing the embedding distance during model inference.
Deep Learning-based Group Causal Inference in Multivariate Time-series
Causal inference in a nonlinear system of multivariate timeseries is instrumental in disentangling the intricate web of relationships among variables, enabling us to make more accurate predictions and gain deeper insights into real-world complex systems.
Let's Get the FACS Straight -- Reconstructing Obstructed Facial Features
As a result, existing facial analysis methods can be used without further changes with respect to the data.
Deep Learning Pipeline for Automated Visual Moth Monitoring: Insect Localization and Species Classification
Biodiversity monitoring is crucial for tracking and counteracting adverse trends in population fluctuations.
Automated Visual Monitoring of Nocturnal Insects with Light-based Camera Traps
We used this dataset to develop and evaluate a two-stage pipeline for insect detection and moth species classification in previous work.
Simplified Concrete Dropout -- Improving the Generation of Attribution Masks for Fine-grained Classification
It utilizes the concrete dropout (CD) to sample a set of attribution masks and updates the sampling parameters based on the output of the classification model.
Improving Data Efficiency for Plant Cover Prediction with Label Interpolation and Monte-Carlo Cropping
The plant community composition is an essential indicator of environmental changes and is, for this reason, usually analyzed in ecological field studies in terms of the so-called plant cover.
Is it worth it? Comparing six deep and classical methods for unsupervised anomaly detection in time series
Detecting anomalies in time series data is important in a variety of fields, including system monitoring, healthcare, and cybersecurity.
Time Series Causal Link Estimation under Hidden Confounding using Knockoff Interventions
We compare our results on synthetic data to those of a time series deconfounding method both with and without estimated confounders.
Causal Discovery using Model Invariance through Knockoff Interventions
Cause-effect analysis is crucial to understand the underlying mechanism of a system.
Image Classification With Small Datasets: Overview and Benchmark
However, as research in this scope is still in its infancy, two key ingredients are missing for ensuring reliable and truthful progress: a systematic and extensive overview of the state of the art, and a common benchmark to allow for objective comparisons between published methods.
Domain Adaptation and Active Learning for Fine-Grained Recognition in the Field of Biodiversity
We discovered that domain adaptation works very well for fine-grained recognition and that the normalization methods have a great influence on the results.
A Strong Baseline for the VIPriors Data-Efficient Image Classification Challenge
Learning from limited amounts of data is the hallmark of intelligence, requiring strong generalization and abstraction skills.
Causal Inference in Non-linear Time-series using Deep Networks and Knockoff Counterfactuals
Overall our method outperforms the widely used vector autoregressive Granger causality and PCMCI in detecting nonlinear causal dependency in multivariate time series.
Anomaly Attribution of Multivariate Time Series using Counterfactual Reasoning
There are numerous methods for detecting anomalies in time series, but that is only the first step to understanding them.
Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification
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.
Ranked #1 on
Small Data Image Classification
on DEIC Benchmark
WikiChurches: A Fine-Grained Dataset of Architectural Styles with Real-World Challenges
We introduce a novel dataset for architectural style classification, consisting of 9, 485 images of church buildings.
Automatic Plant Cover Estimation with Convolutional Neural Networks
Monitoring the responses of plants to environmental changes is essential for plant biodiversity research.
Self-Supervised Learning from Semantically Imprecise Data
Learning from imprecise labels such as "animal" or "bird", but making precise predictions like "snow bunting" at inference time is an important capability for any classifier when expertly labeled training data is scarce.
EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction task
We frame Earth surface forecasting as the task of predicting satellite imagery conditioned on future weather.
Ranked #5 on
Earth Surface Forecasting
on EarthNet2021 OOD Track
Towards Learning an Unbiased Classifier from Biased Data via Conditional Adversarial Debiasing
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
Heuristic methods result in false-positive artifacts because the image after the perturbation is far from the original data distribution.
Analysing the Direction of Emotional Influence in Nonverbal Dyadic Communication: A Facial-Expression Study
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.
EarthNet2021: A novel large-scale dataset and challenge for forecasting localized climate impacts
Here, we define high-resolution Earth surface forecasting as video prediction of satellite imagery conditional on mesoscale weather forecasts.
Content-based Image Retrieval and the Semantic Gap in the Deep Learning Era
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.
Finding Relevant Flood Images on Twitter using Content-based Filters
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.
Making Every Label Count: Handling Semantic Imprecision by Integrating Domain Knowledge
For example, a non-breeding snow bunting is labeled as a bird.
End-to-end Learning of a Fisher Vector Encoding for Part Features in Fine-grained Recognition
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.
Ranked #10 on
Fine-Grained Image Classification
on NABirds
Single-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometry Constrained Keypoints in Real-Time
In this paper we propose a novel 3D single-shot object detection method for detecting vehicles in monocular RGB images.
Visibility Guided NMS: Efficient Boosting of Amodal Object Detection in Crowded Traffic Scenes
Object detection is an important task in environment perception for autonomous driving.
Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detection
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.
Active and Incremental Learning with Weak Supervision
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.
LOST: A flexible framework for semi-automatic image annotation
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
As a countermeasure, we propose a method that automatically analyzes the plausibility of facial behavior based on a sequence of 3D face scans.
Predicting Landscapes from Environmental Conditions Using Generative Networks
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
Fine-grained visual categorization is a classification task for distinguishing categories with high intra-class and small inter-class variance.
Ranked #14 on
Fine-Grained Image Classification
on NABirds
Self-supervised Data Bootstrapping for Deep Optical Character Recognition of Identity Documents
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
Optical Character Recognition (OCR)
Enhancing Flood Impact Analysis using Interactive Retrieval of Social Media Images
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.
Do We Train on Test Data? Purging CIFAR of Near-Duplicates
However, we find that 3. 3% and 10% of the images from the test sets of these datasets have duplicates in the training set.
Deep Learning on Small Datasets without Pre-Training using Cosine Loss
The categorical cross-entropy loss after softmax activation is the method of choice for classification.
Towards Automatic Identification of Elephants in the Wild
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
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.
Integrating domain knowledge: using hierarchies to improve deep classifiers
In this paper, we propose to make use of preexisting class hierarchies like WordNet to integrate additional domain knowledge into classification.
Causal Inference in Nonverbal Dyadic Communication with Relevant Interval Selection and Granger Causality
Human nonverbal emotional communication in dyadic dialogs is a process of mutual influence and adaptation.
Hierarchy-based Image Embeddings for Semantic Image Retrieval
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.
Active Learning for Deep Object Detection
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.
Information-Theoretic Active Learning for Content-Based Image Retrieval
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.
Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detection
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.
Automatic Query Image Disambiguation for Content-Based Image Retrieval
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.
Her2 Challenge Contest: A Detailed Assessment of Automated Her2 Scoring Algorithms in Whole Slide Images of Breast Cancer Tissues
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.
Generalized orderless pooling performs implicit salient matching
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
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.
Automatic Classification of Cancerous Tissue in Laserendomicroscopy Images of the Oral Cavity using Deep Learning
For this work, CLE image sequences (7894 images) from patients diagnosed with OSCC were obtained from 4 specific locations in the oral cavity, including the OSCC lesion.
Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changes
The demands on visual recognition systems do not end with the complexity offered by current large-scale image datasets, such as ImageNet.
ImageNet pre-trained models with batch normalization
Convolutional neural networks (CNN) pre-trained on ImageNet are the backbone of most state-of-the-art approaches.
Maximally Divergent Intervals for Anomaly Detection
We present new methods for batch anomaly detection in multivariate time series.
Fine-grained Recognition in the Noisy Wild: Sensitivity Analysis of Convolutional Neural Networks Approaches
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
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
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.
Neither Quick Nor Proper -- Evaluation of QuickProp for Learning Deep Neural Networks
Neural networks and especially convolutional neural networks are of great interest in current computer vision research.
Fine-grained Recognition Datasets for Biodiversity Analysis
In the following paper, we present and discuss challenging applications for fine-grained visual classification (FGVC): biodiversity and species analysis.
Active Learning and Discovery of Object Categories in the Presence of Unnameable Instances
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.
Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding
Classifying single image patches is important in many different applications, such as road detection or scene understanding.
Part Detector Discovery in Deep Convolutional Neural Networks
Current fine-grained classification approaches often rely on a robust localization of object parts to extract localized feature representations suitable for discrimination.
Seeing through bag-of-visual-word glasses: towards understanding quantization effects in feature extraction methods
To answer this question, we present an in-depth analysis of the effect of local feature quantization on human recognition performance.
ARTOS -- Adaptive Real-Time Object Detection System
ARTOS is all about creating, tuning, and applying object detection models with just a few clicks.
Instance-weighted Transfer Learning of Active Appearance Models
Therefore, we present a transfer learning method that is able to learn from related training data using an instance-weighted transfer technique.
Nonparametric Part Transfer for Fine-grained Recognition
In the following paper, we present an approach for finegrained recognition based on a new part detection method.
Fine-grained Categorization -- Short Summary of our Entry for the ImageNet Challenge 2012
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
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.
