Cluster Centers Provide Good First Labels for Object Detection

Learning object detection models with a few labels, is possible due to ingenious few-shot techniques, and due to clever selection of images to be labeled. Few-shot techniques work with as few as 1 to 10 randomized labels per object class. We are curious if performance of randomized label selection can be improved by selecting 1 to 10 labels per...

A Compression and Simulation-Based Approach to Fraud Discovery

With the uptake of digital services in public and private sectors, the formalization of laws is attracting increasing attention. Yet, non-compliant fraudulent behaviours (money laundering, tax evasion, etc.) - practical realizations of violations of law - remain very difficult to formalize, as one does not know the exact formal rules that define...

Improving Model Inference in Industry by Combining Active and Passive Learning

Inferring behavioral models (e.g., state machines) of software systems is an important element of re-engineering activities. Model inference techniques can be categorized as active or passive learning, constructing models by (dynamically) interacting with systems or (statically) analyzing traces, respectively. Application of those techniques in...

Six Challenges for Human-AI Co-learning

The increasing use of ever-smarter AI-technology is changing the way individuals and teams learn and perform their tasks. In hybrid teams, people collaborate with artificially intelligent partners. To utilize the different strengths and weaknesses of human and artificial intelligence, a hybrid team should be designed upon the principles that...

Rapid Annotation Tool to Train Novel Concept Detectors with Active Learning

Annotating a large set of images, especially with bounding boxes, is a tedious task. In this paper, we propose an intuitive image annotation tool. This tool not only allows (non-expert) users to annotate images with novel concepts, but is also able to achieve acceptable performance with a smaller number of annotated images. The tool can also...

Pitfalls in applying model learning to industrial legacy software

Maintaining legacy software is one of the most common struggles of the software industry, being costly yet essential. We tackle that problem by providing better understanding of software by extracting behavioural models using the model learning technique. The used technique interacts with a running component and extracts abstract models that...

Flexible image analysis for law enforcement agencies with deep neural networks to determine: Where, who and what

Due to the increasing need for effective security measures and the integration of cameras in commercial products, a huge amount of visual data is created today. Law enforcement agencies (LEAs) are inspecting images and videos to find radicalization, propaganda for terrorist organizations and illegal products on darknet markets. This is time...

Improving active Mealy machine learning for protocol conformance testing

Using a well-known industrial case study from the verification literature, the bounded retransmission protocol, we show how active learning can be used to establish the correctness of protocol implementation I relative to a given reference implementation R. Using active learning, we learn a model M R of reference implementation R, which serves...

Active learning of nondeterministic systems from an ioco perspective

Model-based testing allows the creation of test cases from a model of the system under test. Often, such models are difficult to obtain, or even not available. Automata learning helps in inferring the model of a system by observing its behaviour. The model can be employed for many purposes, such as testing other implementations, regression...