Clemens-Alexander Brust

Tim Sonnekalb, Bernd Gruner, Clemens-Alexander Brust et al.

Transformer networks such as CodeBERT already achieve outstanding results for code clone detection in benchmark datasets, so one could assume that this task has already been solved. However, code clone detection is not a trivial task. Semantic code clones, in particular, are challenging to detect. We show that the generalizability of CodeBERT decreases by evaluating two different subsets of Java code clones from BigCloneBench. We observe a significant drop in F1 score when we evaluate different code snippets and functionality IDs than those used for model building.

Bernd Gruner, Tim Sonnekalb, Thomas S. Heinze et al.

Optional type annotations allow for enriching dynamic programming languages with static typing features like better Integrated Development Environment (IDE) support, more precise program analysis, and early detection and prevention of type-related runtime errors. Machine learning-based type inference promises interesting results for automating this task. However, the practical usage of such systems depends on their ability to generalize across different domains, as they are often applied outside their training domain. In this work, we investigate Type4Py as a representative of state-of-the-art deep learning-based type inference systems, by conducting extensive cross-domain experiments. Thereby, we address the following problems: class imbalances, out-of-vocabulary words, dataset shifts, and unknown classes. To perform such experiments, we use the datasets ManyTypes4Py and CrossDomainTypes4Py. The latter we introduce in this paper. Our dataset enables the evaluation of type inference systems in different domains of software projects and has over 1,000,000 type annotations mined on the platforms GitHub and Libraries. It consists of data from the two domains web development and scientific calculation. Through our experiments, we detect that the shifts in the dataset and the long-tailed distribution with many rare and unknown data types decrease the performance of the deep learning-based type inference system drastically. In this context, we test unsupervised domain adaptation methods and fine-tuning to overcome these issues. Moreover, we investigate the impact of out-of-vocabulary words.

Clemens-Alexander Brust, Tim Sonnekalb, Bernd Gruner

Automatic vulnerability detection on C/C++ source code has benefitted from the introduction of machine learning to the field, with many recent publications targeting this combination. In contrast, assembly language or machine code artifacts receive less attention, although there are compelling reasons to study them. They are more representative of what is executed, more easily incorporated in dynamic analysis, and in the case of closed-source code, there is no alternative. We evaluate the representative capability of assembly language compared to C/C++ source code for vulnerability detection. Furthermore, we investigate the role of call graph context in detecting function-spanning vulnerabilities. Finally, we verify whether compiling a benchmark dataset compromises an experiment's soundness by inadvertently leaking label information. We propose ROMEO, a publicly available, reproducible and reusable binary vulnerability detection benchmark dataset derived from the synthetic Juliet test suite. Alongside, we introduce a simple text-based assembly language representation that includes context for function-spanning vulnerability detection and semantics to detect high-level vulnerabilities. It is constructed by disassembling the .text segment of the respective binaries. We evaluate an x86 assembly language representation of the compiled dataset, combined with an off-the-shelf classifier. It compares favorably to state-of-the-art methods, including those operating on the full C/C++ code. Including context information using the call graph improves detection of function-spanning vulnerabilities. There is no label information leaked during the compilation process.

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 expertly labeled training data is scarce. Contributions by volunteers or results of web crawling lack precision in this manner, but are still valuable. And crucially, these weakly labeled examples are available in larger quantities for lower cost than high-quality bespoke training data. CHILLAX, a recently proposed method to tackle this task, leverages a hierarchical classifier to learn from imprecise labels. However, it has two major limitations. First, it does not learn from examples labeled as the root of the hierarchy, e.g., "object". Second, an extrapolation of annotations to precise labels is only performed at test time, where confident extrapolations could be already used as training data. In this work, we extend CHILLAX with a self-supervised scheme using constrained semantic extrapolation to generate pseudo-labels. This addresses the second concern, which in turn solves the first problem, enabling an even weaker supervision requirement than CHILLAX. We evaluate our approach empirically, showing that our method allows for a consistent accuracy improvement of 0.84 to 1.19 percent points over CHILLAX and is suitable as a drop-in replacement without any negative consequences such as longer training times.

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 been research focused on mitigating the effects of label noise. It is typically modeled as inaccuracy, where the correct label is replaced by an incorrect label from the same set. We consider an additional dimension of label noise: imprecision. For example, a non-breeding snow bunting is labeled as a bird. This label is correct, but not as precise as the task requires. Standard softmax classifiers cannot learn from such a weak label because they consider all classes mutually exclusive, which non-breeding snow bunting and bird are not. We propose CHILLAX (Class Hierarchies for Imprecise Label Learning and Annotation eXtrapolation), a method based on hierarchical classification, to fully utilize labels of any precision. Experiments on noisy variants of NABirds and ILSVRC2012 show that our method outperforms strong baselines by as much as 16.4 percentage points, and the current state of the art by up to 3.9 percentage points.

Clemens-Alexander Brust, Christoph Käding, Joachim Denzler

Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both funding and expertise. 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. In this work, we describe combinations of an incremental learning scheme and methods of active learning. These allow for continuous exploration of newly observed unlabeled data. We describe selection criteria based on model uncertainty as well as expected model output change (EMOC). An object detection task is evaluated in a continuous exploration context on the PASCAL VOC dataset. We also validate a weakly supervised system based on active and incremental learning in a real-world biodiversity application where images from camera traps are analyzed. Labeling only 32 images by accepting or rejecting proposals generated by our method yields an increase in accuracy from 25.4% to 42.6%.

Clemens-Alexander Brust, Joachim Denzler

One of the most prominent problems in machine learning in the age of deep learning is the availability of sufficiently large annotated datasets. For specific domains, e.g. animal species, a long-tail distribution means that some classes are observed and annotated insufficiently. Additional labels can be prohibitively expensive, e.g. because domain experts need to be involved. However, there is more information available that is to the best of our knowledge not exploited accordingly. In this paper, we propose to make use of preexisting class hierarchies like WordNet to integrate additional domain knowledge into classification. We encode the properties of such a class hierarchy into a probabilistic model. From there, we derive a novel label encoding and a corresponding loss function. On the ImageNet and NABirds datasets our method offers a relative improvement of 10.4% and 9.6% in accuracy over the baseline respectively. After less than a third of training time, it is already able to match the baseline's fine-grained recognition performance. Both results show that our suggested method is efficient and effective.

Clemens-Alexander Brust, Joachim Denzler

Knowledge transfer, zero-shot learning and semantic image retrieval are methods that aim at improving accuracy by utilizing semantic information, e.g. from WordNet. It is assumed that this information can augment or replace missing visual data in the form of labeled training images because semantic similarity correlates with visual similarity. This assumption may seem trivial, but is crucial for the application of such semantic methods. Any violation can cause mispredictions. Thus, it is important to examine the visual-semantic relationship for a certain target problem. 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. We postulate and verify three highly consequential hypotheses on the relationship. Our results show that it indeed exists and that WordNet semantic similarity carries more information about visual similarity than just the knowledge of "different classes look different". They suggest that classification is not the ideal application for semantic methods and that wrong semantic information is much worse than none.

Clemens-Alexander Brust, Christoph Käding, Joachim Denzler

The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly. Active learning can make the process of labeling new data more efficient by selecting unlabeled samples which, when labeled, are expected to improve the model the most. 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. We propose a set of uncertainty-based active learning metrics suitable for most object detectors. Furthermore, we present an approach to leverage class imbalances during sample selection. All methods are evaluated systematically in a continuous exploration context on the PASCAL VOC 2012 dataset.

Clemens-Alexander Brust, Sven Sickert, Marcel Simon et al.

Neural networks and especially convolutional neural networks are of great interest in current computer vision research. However, many techniques, extensions, and modifications have been published in the past, which are not yet used by current approaches. In this paper, we study the application of a method called QuickProp for training of deep neural networks. In particular, we apply QuickProp during learning and testing of fully convolutional networks for the task of semantic segmentation. We compare QuickProp empirically with gradient descent, which is the current standard method. Experiments suggest that QuickProp can not compete with standard gradient descent techniques for complex computer vision tasks like semantic segmentation.

Clemens-Alexander Brust, Sven Sickert, Marcel Simon et al.

Classifying single image patches is important in many different applications, such as road detection or scene understanding. In this paper, we present convolutional patch networks, which are convolutional networks learned to distinguish different image patches and which can be used for pixel-wise labeling. We also show how to incorporate spatial information of the patch as an input to the network, which allows for learning spatial priors for certain categories jointly with an appearance model. In particular, we focus on road detection and urban scene understanding, two application areas where we are able to achieve state-of-the-art results on the KITTI as well as on the LabelMeFacade dataset. Furthermore, our paper offers a guideline for people working in the area and desperately wandering through all the painstaking details that render training CNs on image patches extremely difficult.