113 citations · 362 across the 18 of their papers we have counts for
22 papers
Prompt-Tuning SAM: From Generalist to Specialist with only 2048 Parameters and 16 Training Images
Tristan Piater, Björn Barz, Alexander Freytag
The Segment Anything Model (SAM) is widely used for segmenting a diverse range of objects in natural images from simple user prompts like points or bounding boxes. However, SAM's p…
Image Classification with Small Datasets: Overview and Benchmark
L. Brigato, B. Barz, L. Iocchi +1
Image classification with small datasets has been an active research area in the recent past. However, as research in this scope is still in its infancy, two key ingredients are mi…
Domain Adaptation and Active Learning for Fine-Grained Recognition in the Field of Biodiversity
Bernd Gruner, Matthias Körschens, Björn Barz +1
Deep-learning methods offer unsurpassed recognition performance in a wide range of domains, including fine-grained recognition tasks. However, in most problem areas there are insuf…
A Strong Baseline for the VIPriors Data-Efficient Image Classification Challenge
Björn Barz, Lorenzo Brigato, Luca Iocchi +1
Learning from limited amounts of data is the hallmark of intelligence, requiring strong generalization and abstraction skills. In a machine learning context, data-efficient methods…
Anomaly Attribution of Multivariate Time Series using Counterfactual Reasoning
Violeta Teodora Trifunov, Maha Shadaydeh, Björn Barz +1
There are numerous methods for detecting anomalies in time series, but that is only the first step to understanding them. We strive to exceed this by explaining those anomalies. Th…
Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification
Lorenzo Brigato, Björn Barz, Luca Iocchi +1
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 p…
WikiChurches: A Fine-Grained Dataset of Architectural Styles with Real-World Challenges
Björn Barz, Joachim Denzler
We introduce a novel dataset for architectural style classification, consisting of 9,485 images of church buildings. Both images and style labels were sourced from Wikipedia. The d…
Self-Supervised Learning from Semantically Imprecise Data
Clemens-Alexander Brust, Björn Barz, Joachim Denzler
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 e…
Content-based Image Retrieval and the Semantic Gap in the Deep Learning Era
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 imag…
Finding Relevant Flood Images on Twitter using Content-based Filters
Björn Barz, Kai Schröter, Ann-Christin Kra +1
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. At the same time, a plet…
Making Every Label Count: Handling Semantic Imprecision by Integrating Domain Knowledge
Clemens-Alexander Brust, Björn Barz, Joachim Denzler
Noisy data, crawled from the web or supplied by volunteers such as Mechanical Turkers or citizen scientists, is considered an alternative to professionally labeled data. There has…
Enhancing Flood Impact Analysis using Interactive Retrieval of Social Media Images
Björn Barz, Kai Schröter, Moritz Münch +4
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. This limitation coul…
Do We Train on Test Data? Purging CIFAR of Near-Duplicates
Björn Barz, Joachim Denzler
The CIFAR-10 and CIFAR-100 datasets are two of the most heavily benchmarked datasets in computer vision and are often used to evaluate novel methods and model architectures in the…
Deep Learning on Small Datasets without Pre-Training using Cosine Loss
Björn Barz, Joachim Denzler
Two things seem to be indisputable in the contemporary deep learning discourse: 1. The categorical cross-entropy loss after softmax activation is the method of choice for classific…
Towards Automatic Identification of Elephants in the Wild
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 in…
Hierarchy-based Image Embeddings for Semantic Image Retrieval
Björn Barz, Joachim Denzler
Deep neural networks trained for classification have been found to learn powerful image representations, which are also often used for other tasks such as comparing images w.r.t. t…
Information-Theoretic Active Learning for Content-Based Image Retrieval
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…
Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detection
Björn Barz, Erik Rodner, Yanira Guanche Garcia +1
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
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 us…
Fast Learning and Prediction for Object Detection using Whitened CNN Features
Björn Barz, Erik Rodner, Christoph Käding +1
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…
Maximally Divergent Intervals for Anomaly Detection
Erik Rodner, Björn Barz, Yanira Guanche +5
We present new methods for batch anomaly detection in multivariate time series. Our methods are based on maximizing the Kullback-Leibler divergence between the data distribution wi…
ARTOS -- Adaptive Real-Time Object Detection System
Björn Barz, Erik Rodner, Joachim Denzler
ARTOS is all about creating, tuning, and applying object detection models with just a few clicks. In particular, ARTOS facilitates learning of models for visual object detection by…