Refine
Document Type
- Conference Proceeding (45)
- Article (unreviewed) (16)
- Article (reviewed) (5)
- Book (2)
- Part of a Book (2)
- Doctoral Thesis (1)
- Report (1)
Conference Type
- Konferenzartikel (43)
- Konferenz-Abstract (1)
- Sonstiges (1)
Has Fulltext
- no (72) (remove)
Is part of the Bibliography
- yes (72)
Keywords
- Deep Leaning (9)
- Machine Learning (8)
- Robustness (4)
- Data Science (3)
- Generative Adversarial Network (3)
- image classification (3)
- Aliasing (2)
- CNNs (2)
- Computer Vision (2)
- Künstliche Intelligenz (2)
Institute
- IMLA - Institute for Machine Learning and Analytics (72) (remove)
Open Access
- Open Access (49)
- Bronze (15)
- Closed Access (11)
- Closed (10)
- Diamond (9)
- Grün (2)
- Gold (1)
- Hybrid (1)
Most eCommerce applications, like web-shops have millions of products. In this context, the identification of similar products is a common sub-task, which can be utilized in the implementation of recommendation systems, product search engines and internal supply logistics. Providing this data set, our goal is to boost the evaluation of machine learning methods for the prediction of the category of the retail products from tuples of images and descriptions.
Deep learning models are intrinsically sensitive to distribution shifts in the input data. In particular, small, barely perceivable perturbations to the input data can force models to make wrong predictions with high confidence. An common defense mechanism is regularization through adversarial training which injects worst-case perturbations back into training to strengthen the decision boundaries, and to reduce overfitting. In this context, we perform an investigation of 3 × 3 convolution filters that form in adversarially- trained models. Filters are extracted from 71 public models of the ℓ ∞ -RobustBench CIFAR-10/100 and ImageNet1k leaderboard and compared to filters extracted from models built on the same architectures but trained without robust regularization. We observe that adversarially-robust models appear to form more diverse, less sparse, and more orthogonal convolution filters than their normal counterparts. The largest differences between robust and normal models are found in the deepest layers, and the very first convolution layer, which consistently and predominantly forms filters that can partially eliminate perturbations, irrespective of the architecture.
Many commonly well-performing convolutional neural network models have shown to be susceptible to input data perturbations, indicating a low model robustness. To reveal model weaknesses, adversarial attacks are specifically optimized to generate small, barely perceivable image perturbations that flip the model prediction. Robustness against attacks can be gained by using adversarial examples during training, which in most cases reduces the measurable model attackability. Unfortunately, this technique can lead to robust overfitting, which results in non-robust models. In this paper, we analyze adversarially trained, robust models in the context of a specific network operation, the downsampling layer, and provide evidence that robust models have learned to downsample more accurately and suffer significantly less from downsampling artifacts, aka. aliasing, than baseline models. In the case of robust overfitting, we observe a strong increase in aliasing and propose a novel early stopping approach based on the measurement of aliasing.
Many commonly well-performing convolutional neural network models have shown to be susceptible to input data perturbations, indicating a low model robustness. Adversarial attacks are thereby specifically optimized to reveal model weaknesses, by generating small, barely perceivable image perturbations that flip the model prediction. Robustness against attacks can be gained for example by using adversarial examples during training, which effectively reduces the measurable model attackability. In contrast, research on analyzing the source of a model’s vulnerability is scarce. In this paper, we analyze adversarially trained, robust models in the context of a specifically suspicious network operation, the downsampling layer, and provide evidence that robust models have learned to downsample more accurately and suffer significantly less from aliasing than baseline models.
Due to its performance, the field of deep learning has gained a lot of attention, with neural networks succeeding in areas like Computer Vision (CV), Neural Language Processing (NLP), and Reinforcement Learning (RL). However, high accuracy comes at a computational cost as larger networks require longer training time and no longer fit onto a single GPU. To reduce training costs, researchers are looking into the dynamics of different optimizers, in order to find ways to make training more efficient. Resource requirements can be limited by reducing model size during training or designing more efficient models that improve accuracy without increasing network size.
This thesis combines eigenvalue computation and high-dimensional loss surface visualization to study different optimizers and deep neural network models. Eigenvectors of different eigenvalues are computed, and the loss landscape and optimizer trajectory are projected onto the plane spanned by those eigenvectors. A new parallelization method for the stochastic Lanczos method is introduced, resulting in faster computation and thus enabling high-resolution videos of the trajectory and secondorder information during neural network training. Additionally, the thesis presents the loss landscape between two minima along with the eigenvalue density spectrum at intermediate points for the first time.
Secondly, this thesis presents a regularization method for Generative Adversarial Networks (GANs) that uses second-order information. The gradient during training is modified by subtracting the eigenvector direction of the biggest eigenvalue, preventing the network from falling into the steepest minima and avoiding mode collapse. The thesis also shows the full eigenvalue density spectra of GANs during training.
Thirdly, this thesis introduces ProxSGD, a proximal algorithm for neural network training that guarantees convergence to a stationary point and unifies multiple popular optimizers. Proximal gradients are used to find a closed-form solution to the problem of training neural networks with smooth and non-smooth regularizations, resulting in better sparsity and more efficient optimization. Experiments show that ProxSGD can find sparser networks while reaching the same accuracy as popular optimizers.
Lastly, this thesis unifies sparsity and neural architecture search (NAS) through the framework of group sparsity. Group sparsity is achieved through ℓ2,1-regularization during training, allowing for filter and operation pruning to reduce model size with minimal sacrifice in accuracy. By grouping multiple operations together, group sparsity can be used for NAS as well. This approach is shown to be more robust while still achieving competitive accuracies compared to state-of-the-art methods
An Empirical Investigation of Model-to-Model Distribution Shifts in Trained Convolutional Filters
(2021)
We present first empirical results from our ongoing investigation of distribution shifts in image data used for various computer vision tasks. Instead of analyzing the original training and test data, we propose to study shifts in the learned weights of trained models. In this work, we focus on the properties of the distributions of dominantly used 3x3 convolution filter kernels. We collected and publicly provide a data set with over half a billion filters from hundreds of trained CNNs, using a wide range of data sets, architectures, and vision tasks. Our analysis shows interesting distribution shifts (or the lack thereof) between trained filters along different axes of meta-parameters, like data type, task, architecture, or layer depth. We argue, that the observed properties are a valuable source for further investigation into a better understanding of the impact of shifts in the input data to the generalization abilities of CNN models and novel methods for more robust transfer-learning in this domain.
Neural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by small perturbations to inputs that are often imperceivable to humans and do not have to carry semantic meaning. Adversarial training poses a partial solution to address this issue by training models on worst-case perturbations. Yet, recent work has also pointed out that the reasoning in neural networks is different from humans. Humans identify objects by shape, while neural nets mainly employ texture cues. Exemplarily, a model trained on photographs will likely fail to generalize to datasets containing sketches. Interestingly, it was also shown that adversarial training seems to favorably increase the shift toward shape bias. In this work, we revisit this observation and provide an extensive analysis of this effect on various architectures, the common L_2-and L_-training, and Transformer-based models. Further, we provide a possible explanation for this phenomenon from a frequency perspective.
Apache Hadoop is a well-known open-source framework for storing and processing huge amounts of data. This paper shows the usage of the framework within a project of the university in cooperation with a semiconductor company. The goal of this project was to supplement the existing data landscape by the facilities of storing and analyzing the data on a new Apache Hadoop based platform.
Motivated by the recent trend towards the usage of larger receptive fields for more context-aware neural networks in vision applications, we aim to investigate how large these receptive fields really need to be. To facilitate such study, several challenges need to be addressed, most importantly: (i) We need to provide an effective way for models to learn large filters (potentially as large as the input data) without increasing their memory consumption during training or inference, (ii) the study of filter sizes has to be decoupled from other effects such as the network width or number of learnable parameters, and (iii) the employed convolution operation should be a plug-and-play module that can replace any conventional convolution in a Convolutional Neural Network (CNN) and allow for an efficient implementation in current frameworks. To facilitate such models, we propose to learn not spatial but frequency representations of filter weights as neural implicit functions, such that even infinitely large filters can be parameterized by only a few learnable weights. The resulting neural implicit frequency CNNs are the first models to achieve results on par with the state-of-the-art on large image classification benchmarks while executing convolutions solely in the frequency domain and can be employed within any CNN architecture. They allow us to provide an extensive analysis of the learned receptive fields. Interestingly, our analysis shows that, although the proposed networks could learn very large convolution kernels, the learned filters practically translate into well-localized and relatively small convolution kernels in the spatial domain.
Currently, many theoretical as well as practically relevant questions towards the transferability and robustness of Convolutional Neural Networks (CNNs) remain unsolved. While ongoing research efforts are engaging these problems from various angles, in most computer vision related cases these approaches can be generalized to investigations of the effects of distribution shifts in image data. In this context, we propose to study the shifts in the learned weights of trained CNN models. Here we focus on the properties of the distributions of dominantly used 3×3 convolution filter kernels. We collected and publicly provide a dataset with over 1.4 billion filters from hundreds of trained CNNs, using a wide range of datasets, architectures, and vision tasks. In a first use case of the proposed dataset, we can show highly relevant properties of many publicly available pre-trained models for practical applications: I) We analyze distribution shifts (or the lack thereof) between trained filters along different axes of meta-parameters, like visual category of the dataset, task, architecture, or layer depth. Based on these results, we conclude that model pre-training can succeed on arbitrary datasets if they meet size and variance conditions. II) We show that many pre-trained models contain degenerated filters which make them less robust and less suitable for fine-tuning on target applications. Data & Project website: https://github.com/paulgavrikov/cnn-filter-db.
Generative adversarial networks (GANs) provide state-of-the-art results in image generation. However, despite being so powerful, they still remain very challenging to train. This is in particular caused by their highly non-convex optimization space leading to a number of instabilities. Among them, mode collapse stands out as one of the most daunting ones. This undesirable event occurs when the model can only fit a few modes of the data distribution, while ignoring the majority of them. In this work, we combat mode collapse using second-order gradient information. To do so, we analyse the loss surface through its Hessian eigenvalues, and show that mode collapse is related to the convergence towards sharp minima. In particular, we observe how the eigenvalues of the G are directly correlated with the occurrence of mode collapse. Finally, motivated by these findings, we design a new optimization algorithm called nudged-Adam (NuGAN) that uses spectral information to overcome mode collapse, leading to empirically more stable convergence properties.
Generative adversarial networks (GANs) provide state-of-the-art results in image generation. However, despite being so powerful, they still remain very challenging to train. This is in particular caused by their highly non-convex optimization space leading to a number of instabilities. Among them, mode collapse stands out as one of the most daunting ones. This undesirable event occurs when the model can only fit a few modes of the data distribution, while ignoring the majority of them. In this work, we combat mode collapse using second-order gradient information. To do so, we analyse the loss surface through its Hessian eigenvalues, and show that mode collapse is related to the convergence towards sharp minima. In particular, we observe how the eigenvalues of the are directly correlated with the occurrence of mode collapse. Finally, motivated by these findings, we design a new optimization algorithm called nudged-Adam (NuGAN) that uses spectral information to overcome mode collapse, leading to empirically more stable convergence properties.
Transformer models have recently attracted much interest from computer vision researchers and have since been successfully employed for several problems traditionally addressed with convolutional neural networks. At the same time, image synthesis using generative adversarial networks (GANs) has drastically improved over the last few years. The recently proposed TransGAN is the first GAN using only transformer-based architectures and achieves competitive results when compared to convolutional GANs. However, since transformers are data-hungry architectures, TransGAN requires data augmentation, an auxiliary super-resolution task during training, and a masking prior to guide the self-attention mechanism. In this paper, we study the combination of a transformer-based generator and convolutional discriminator and successfully remove the need of the aforementioned required design choices. We evaluate our approach by conducting a benchmark of well-known CNN discriminators, ablate the size of the transformer-based generator, and show that combining both architectural elements into a hybrid model leads to better results. Furthermore, we investigate the frequency spectrum properties of generated images and observe that our model retains the benefits of an attention based generator.
Data Science
(2019)
Data Science steht derzeit wie kein anderer Begriff für die Auswertung großer Datenmengen mit analytischen Konzepten des Machine Learning oder der künstlichen Intelligenz. Nach der bewussten Wahrnehmung der Big Data und dabei insbesondere der Verfügbarmachung in Unternehmen sind Technologien und Methoden zur Auswertung dort gefordert, wo klassische Business Intelligence an ihre Grenzen stößt.
Dieses Buch bietet eine umfassende Einführung in Data Science und deren praktische Relevanz für Unternehmen. Dabei wird auch die Integration von Data Science in ein bereits bestehendes Business-Intelligence-Ökosystem thematisiert. In verschiedenen Beiträgen werden sowohl Aufgabenfelder und Methoden als auch Rollen- und Organisationsmodelle erläutert, die im Zusammenspiel mit Konzepten und Architekturen auf Data Science wirken. Neben den Grundlagen werden unter anderem folgende Themen behandelt:
- Data Science und künstliche Intelligenz
- Konzeption und Entwicklung von Data-driven Products
- Deep Learning
- Self-Service im Data-Science-Umfeld
- Data Privacy und Fragen zur digitalen Ethik
- Customer Churn mit Keras/TensorFlow und H2O
- Wirtschaftlichkeitsbetrachtung bei der Auswahl und Entwicklung von Data Science
- Predictive Maintenance
- Scrum in Data-Science-Projekten
Zahlreiche Anwendungsfälle und Praxisbeispiele geben Einblicke in die aktuellen Erfahrungen bei Data-Science-Projekten und erlauben dem Leser einen direkten Transfer in die tägliche Arbeit.
Data Science
(2021)
Know-how für Data Scientists
• Übersichtliche und anwendungsbezogene Einführung
• Zahlreiche Anwendungsfälle und Praxisbeispiele aus unterschiedlichen Branchen
• Potenziale, aber auch mögliche Fallstricke werden aufgezeigt
Data Science steht derzeit wie kein anderer Begriff für die Auswertung großer Datenmengen mit analytischen Konzepten des Machine Learning oder der künstlichen Intelligenz. Nach der bewussten Wahrnehmung der Big Data und dabei insbesondere der Verfügbarmachung in Unternehmen sind Technologien und Methoden zur Auswertung dort gefordert, wo klassische Businss Intelligence an ihre Grenzen stößt.
Dieses Buch bietet eine umfassende Einführung in Data Science und deren praktische Relevanz für Unternehmen. Dabei wird auch die Integration von Data Science in ein bereits bestehendes Business-Intelligence-Ökosystem thematisiert. In verschiedenen Beiträgen werden sowohl Aufgabenfelder und Methoden als auch Rollen- und Organisationsmodelle erläutert, die im Zusammenspiel mit Konzepten und Architekturen auf Data Science wirken.
Diese 2., überarbeitete Auflage wurde um neue Themen wie Feature Selection und Deep Reinforcement Learning sowie eine neue Fallstudie erweitert.
Seismic data processing involves techniques to deal with undesired effects that occur during acquisition and pre-processing. These effects mainly comprise coherent artefacts such as multiples, non-coherent signals such as electrical noise, and loss of signal information at the receivers that leads to incomplete traces. In this work, we employ a generative solution, since it can explicitly model complex data distributions and hence, yield to a better decision-making process. In particular, we introduce diffusion models for multiple removal. To that end, we run experiments on synthetic and on real data, and we compare the deep diffusion performance with standard algorithms. We believe that our pioneer study not only demonstrates the capability of diffusion models, but also opens the door to future research to integrate generative models in seismic workflows.
An important step in seismic data processing to improve inversion and interpretation is multiples attenuation. Radon-based algorithms are often used for discriminating primaries and multiples. Recently, deep learning (DL), based on convolutional neural networks (CNNs) has shown promising results in demultiple that could mitigate the challenges of Radon-based methods. In this work, we investigate new different strategies to train a CNN for multiples removal based on different loss functions. We propose combined primaries and multiples labels in the loss for training a CNN to predict primaries, multiples, or both simultaneously. We evaluate the performance of the CNNs trained with the different strategies on 400 clean and noisy synthetic data, considering 3 metrics. We found that training a CNN to predict the multiples and then subtracting them from the input image is the most effective strategy for demultiple. Furthermore, including the primaries labels as a constraint during the training of multiples prediction improves the results. Finally, we test the strategies on a field dataset. The CNNs trained with different strategies report competitive results on real data compared with Radon demultiple. As a result, effectively trained CNN models can potentially replace Radon-based demultiple in existing workflows.
Recently, adversarial attacks on image classification networks by the AutoAttack (Croce and Hein, 2020b) framework have drawn a lot of attention. While AutoAttack has shown a very high attack success rate, most defense approaches are focusing on network hardening and robustness enhancements, like adversarial training. This way, the currently best-reported method can withstand about 66% of adversarial examples on CIFAR10. In this paper, we investigate the spatial and frequency domain properties of AutoAttack and propose an alternative defense. Instead of hardening a network, we detect adversarial attacks during inference, rejecting manipulated inputs. Based on a rather simple and fast analysis in the frequency domain, we introduce two different detection algorithms. First, a black box detector that only operates on the input images and achieves a detection accuracy of 100% on the AutoAttack CIFAR10 benchmark and 99.3% on ImageNet, for epsilon = 8/255 in both cases. Second, a whitebox detector using an analysis of CNN feature maps, leading to a detection rate of also 100% and 98.7% on the same benchmarks.
Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality
(2023)
Diffusion models recently have been successfully applied for the visual synthesis of strikingly realistic appearing images. This raises strong concerns about their potential for malicious purposes. In this paper, we propose using the lightweight multi Local Intrinsic Dimensionality (multiLID), which has been originally developed in context of the detection of adversarial examples, for the automatic detection of synthetic images and the identification of the according generator networks. In contrast to many existing detection approaches, which often only work for GAN-generated images, the proposed method provides close to perfect detection results in many realistic use cases. Extensive experiments on known and newly created datasets demonstrate that the proposed multiLID approach exhibits superiority in diffusion detection and model identification.Since the empirical evaluations of recent publications on the detection of generated images are often mainly focused on the "LSUN-Bedroom" dataset, we further establish a comprehensive benchmark for the detection of diffusion-generated images, including samples from several diffusion models with different image sizes.The code for our experiments is provided at https://github.com/deepfake-study/deepfake-multiLID.
Recent work has investigated the distributions of learned convolution filters through a large-scale study containing hundreds of heterogeneous image models. Surprisingly, on average, the distributions only show minor drifts in comparisons of various studied dimensions including the learned task, image domain, or dataset. However, among the studied image domains, medical imaging models appeared to show significant outliers through "spikey" distributions, and, therefore, learn clusters of highly specific filters different from other domains. Following this observation, we study the collected medical imaging models in more detail. We show that instead of fundamental differences, the outliers are due to specific processing in some architectures. Quite the contrary, for standardized architectures, we find that models trained on medical data do not significantly differ in their filter distributions from similar architectures trained on data from other domains. Our conclusions reinforce previous hypotheses stating that pre-training of imaging models can be done with any kind of diverse image data.