Global Interpretation of Image Classification Models via SEmantic Feature Analysis (SEFA)

Deep learning models have achieved state-of-the-art performance on several image classification tasks over the past years. Several studies claim to approach or even surpass human-levels of performance when using such models to classify images. However, these architectures are notoriously complex, thus making their interpretation a challenge....

Classifying Retail Store Cabinets with Missing or Misplaced Products Using Verification Learning

Performing tasks in dynamic environments is still an open challenge in robotics. To be able to perform a task reliably in such scenarios, the state of the world has to be continuously monitored. In this context, most state-of-the-art perception methods focus on the recognition and classification of individual objects. However, these methods...

Backdoor Attacks in Neural Networks

Deep learning has made tremendous success in the past decade. As a result, it is becoming widely deployed in various safety and security-critical applications like autonomous driving, malware detection, fingerprint identification, and financial fraud detection. It was recently shown that deep neural networks are susceptible to multiple attacks...

Exploration of Deep Learning-based Computer Vision for the detection of floating plastic debris in waterways

Plastic pollution is one of the most challenging global environmental problems. Currently, more than 1000 rivers transport approximately 80% of the plastic influx into the oceans. Naturally, more and more companies are interested in tackling this problem. One of them is Noria Sustainable Innovators, a company based in Delft (Netherlands). It is...

Flowsheet Recognition using Deep Convolutional Neural Networks

Flowsheets are the most important building blocks to define and communicate the structure of chemical processes. Gaining access to large data sets of machine-readable chemical flowsheets could significantly enhance process synthesis through artificial intelligence. A large number of these flowsheets are publicly available in the scientific...

Extracting insights from black box neural networks for network-wide traffic predictions

Accurate and trustworthy short-term traffic prediction is crucial in the modern world for the comfort of drivers and decision-makers as it is used to improve the performance of traffic management systems, lessen congestion, increase safety, and shorten journey times. It is possible to discover useful information for network transportation...

Augment it Maybe?: Improving Deep Vision Models with Adversarial Scene Text Augmentation

Image data augmentation has been regarded as a reliable and effective way to increase the data available for training. With the advent and rise of Generative AI, generative data augmentation has been shown to realize even better gains in performance for downstream tasks. However, these performance gains are often the cause of "extra information"...

Data-efficient resolution transfer with Continuous Kernel Convolutional Neural Networks

Convolutional Neural Networks (CNNs) benefit from fine-grained details in high-resolution images, but these images are not always easily available as data collection can be expensive or time-consuming. Transfer learning pre-trains models on data from a related domain before fine-tuning on the main domain, and is a common strategy to deal with...