Search Results for author:
Found 63 papers, 30 papers with code
Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach
This research makes an important contribution to the development of attribution maps by providing a reliable and consistent evaluation framework.
WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Images
Wood species identification plays a crucial role in various industries, from ensuring the legality of timber products to advancing ecological conservation efforts.
How Do Training Methods Influence the Utilization of Vision Models?
Our findings reveal that the training method strongly influences which layers become critical to the decision function for a given task.
Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigation
This paper introduces Top-GAP, a novel regularization technique that enhances the explainability and robustness of convolutional neural networks.
Can Visual Language Models Replace OCR-Based Visual Question Answering Pipelines in Production? A Case Study in Retail
This paper analyzes the performance and limits of various VLMs in the context of VQA and OCR [5, 9, 12] tasks in a production-level scenario.
Optical Character Recognition
Optical Character Recognition (OCR)
+3
Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration
Image restoration networks are usually comprised of an encoder and a decoder, responsible for aggregating image content from noisy, distorted data and to restore clean, undistorted images, respectively.
Ambiguous Annotations: When is a Pedestrian not a Pedestrian?
Datasets labelled by human annotators are widely used in the training and testing of machine learning models.
Can Biases in ImageNet Models Explain Generalization?
The robust generalization of models to rare, in-distribution (ID) samples drawn from the long tail of the training distribution and to out-of-training-distribution (OOD) samples is one of the major challenges of current deep learning methods.
Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets
In this paper, we emphasize that many datasets for AI-generated image detection contain biases related to JPEG compression and image size.
Urban Sound Propagation: a Benchmark for 1-Step Generative Modeling of Complex Physical Systems
Data-driven modeling of complex physical systems is receiving a growing amount of attention in the simulation and machine learning communities.
Are Vision Language Models Texture or Shape Biased and Can We Steer Them?
If text does indeed influence visual biases, this suggests that we may be able to steer visual biases not just through visual input but also through language: a hypothesis that we confirm through extensive experiments.
Challenging the Black Box: A Comprehensive Evaluation of Attribution Maps of CNN Applications in Agriculture and Forestry
In this study, we explore the explainability of neural networks in agriculture and forestry, specifically in fertilizer treatment classification and wood identification.
Adversarial Examples are Misaligned in Diffusion Model Manifolds
In recent years, diffusion models (DMs) have drawn significant attention for their success in approximating data distributions, yielding state-of-the-art generative results.
Retail-786k: a Large-Scale Dataset for Visual Entity Matching
In this paper, we introduce the first publicly available large-scale dataset for "visual entity matching", based on a production level use case in the retail domain.
Don't Look into the Sun: Adversarial Solarization Attacks on Image Classifiers
Assessing the robustness of deep neural networks against out-of-distribution inputs is crucial, especially in safety-critical domains like autonomous driving, but also in safety systems where malicious actors can digitally alter inputs to circumvent safety guards.
On the Interplay of Convolutional Padding and Adversarial Robustness
It is common practice to apply padding prior to convolution operations to preserve the resolution of feature-maps in Convolutional Neural Networks (CNN).
As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain
To facilitate such a study, several challenges need to be addressed: 1) we need an effective means to train models with large filters (potentially as large as the input data) without increasing the number of learnable parameters 2) the employed convolution operation should be a plug-and-play module that can replace conventional convolutions in a CNN and allow for an efficient implementation in current frameworks 3) the study of filter sizes has to be decoupled from other aspects such as the network width or the number of learnable parameters 4) the cost of the convolution operation itself has to remain manageable i. e. we cannot naively increase the size of the convolution kernel.
Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling
Convolutional neural networks encode images through a sequence of convolutions, normalizations and non-linearities as well as downsampling operations into potentially strong semantic embeddings.
Automating Wood Species Detection and Classification in Microscopic Images of Fibrous Materials with Deep Learning
We have developed a methodology for the systematic generation of a large image dataset of macerated wood references, which we used to generate image data for nine hardwood genera.
On Invariance, Equivariance, Correlation and Convolution of Spherical Harmonic Representations for Scalar and Vectorial Data
The mathematical representations of data in the Spherical Harmonic (SH) domain has recently regained increasing interest in the machine learning community.
Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality
Diffusion models recently have been successfully applied for the visual synthesis of strikingly realistic appearing images.
Fine-Grained Product Classification on Leaflet Advertisements
We show, that the combination of image and text as input improves the classification of visual difficult to distinguish products.
An Extended Study of Human-like Behavior under Adversarial Training
Adversarial training poses a partial solution to address this issue by training models on worst-case perturbations.
The Power of Linear Combinations: Learning with Random Convolutions
Following the traditional paradigm of convolutional neural networks (CNNs), modern CNNs manage to keep pace with more recent, for example transformer-based, models by not only increasing model depth and width but also the kernel size.
Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection
Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks.
Does Medical Imaging learn different Convolution Filters?
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.
Robust Models are less Over-Confident
Further, our analysis of robust models shows that not only AT but also the model's building blocks (like activation functions and pooling) have a strong influence on the models' prediction confidences.
Physics-Informed Learning of Aerosol Microphysics
The original M7 model is used to generate data of input-output pairs to train a neural network on it.
Deep Diffusion Models for Seismic Processing
Seismic data processing involves techniques to deal with undesired effects that occur during acquisition and pre-processing.
Dissecting U-net for Seismic Application: An In-Depth Study on Deep Learning Multiple Removal
To the best of our knowledge, this study pioneers the unboxing of neural networks for the demultiple process, helping the user to gain insights into the inside running of the network.
Adversarial Robustness through the Lens of Convolutional Filters
Deep learning models are intrinsically sensitive to distribution shifts in the input data.
FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting
Over the last years, Convolutional Neural Networks (CNNs) have been the dominating neural architecture in a wide range of computer vision tasks.
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters
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.
Ranked #5 on
Image Classification
on Fashion-MNIST
An Empirical Investigation of Model-to-Model Distribution Shifts in Trained Convolutional Filters
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.
Investigating Shifts in GAN Output-Distributions
In this work, we introduce a loop-training scheme for the systematic investigation of observable shifts between the distributions of real training data and GAN generated data.
Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?
In its most commonly reported sub-task, RobustBench evaluates and ranks the adversarial robustness of trained neural networks on CIFAR10 under AutoAttack (Croce and Hein 2020b) with l-inf perturbations limited to eps = 8/255.
Aliasing coincides with CNNs vulnerability towards adversarial attacks
Many commonly well-performing convolutional neural network models have shown to be susceptible to input data perturbations, indicating a low model robustness.
Detecting AutoAttack Perturbations in the Frequency Domain
Recently, adversarial attacks on image classification networks by the AutoAttack (Croce and Hein, 2020b) framework have drawn a lot of attention.
Emulating Aerosol Microphysics with Machine Learning
This is done in the ECHAM-HAM global climate aerosol model using the M7 microphysics model, but increased computational costs make it very expensive to run at higher resolutions or for a longer time.
Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Space
Over the last decade, the development of deep image classification networks has mostly been driven by the search for the best performance in terms of classification accuracy on standardized benchmarks like ImageNet.
A Retail Product Categorisation Dataset
Most eCommerce applications, like web-shops have millions of products.
SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domain
Despite the success of convolutional neural networks (CNNs) in many computer vision and image analysis tasks, they remain vulnerable against so-called adversarial attacks: Small, crafted perturbations in the input images can lead to false predictions.
Combating Mode Collapse in GAN training: An Empirical Analysis using Hessian Eigenvalues
This undesirable event occurs when the model can only fit a few modes of the data distribution, while ignoring the majority of them.
Latent Space Conditioning on Generative Adversarial Networks
In particular, our approach exploits the structure of a latent space (learned by the representation learning) and employs it to condition the generative model.
Python Workflows on HPC Systems
The recent successes and wide spread application of compute intensive machine learning and data analytics methods have been boosting the usage of the Python programming language on HPC systems.
Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches
In this work, we evaluate two different image clustering objectives, k-means clustering and correlation clustering, in the context of Triplet Loss induced feature space embeddings.
Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions
Generative convolutional deep neural networks, e. g. popular GAN architectures, are relying on convolution based up-sampling methods to produce non-scalar outputs like images or video sequences.
PHS: A Toolbox for Parallel Hyperparameter Search
We introduce an open source python framework named PHS - Parallel Hyperparameter Search to enable hyperparameter optimization on numerous compute instances of any arbitrary python function.
Local Facial Attribute Transfer through Inpainting
The term attribute transfer refers to the tasks of altering images in such a way, that the semantic interpretation of a given input image is shifted towards an intended direction, which is quantified by semantic attributes.
Unsupervised Multiple Person Tracking using AutoEncoder-Based Lifted Multicuts
Our method is based on straight-forward spatio-temporal cues that can be extracted from neighboring frames in an image sequences without superivison.
Scalable Hyperparameter Optimization with Lazy Gaussian Processes
Reducing its computational complexity from cubic to quadratic allows an efficient strong scaling of Bayesian Optimization while outperforming the previous approach regarding optimization accuracy.
Unmasking DeepFakes with simple Features
In this work, we present a simple way to detect such fake face images - so-called DeepFakes.
Semi Few-Shot Attribute Translation
Recent studies have shown remarkable success in image-to-image translation for attribute transfer applications.
GradVis: Visualization and Second Order Analysis of Optimization Surfaces during the Training of Deep Neural Networks
Current training methods for deep neural networks boil down to very high dimensional and non-convex optimization problems which are usually solved by a wide range of stochastic gradient descent methods.
Object Segmentation using Pixel-wise Adversarial Loss
Recent deep learning based approaches have shown remarkable success on object segmentation tasks.
Stabilizing GANs with Soft Octave Convolutions
The basic idea of our approach is to split convolutional filters into additive high and low frequency parts, while shifting weight updates from low to high during the training.
Sparsity in Deep Neural Networks - An Empirical Investigation with TensorQuant
Various approaches have been investigated to reduce the necessary resources, one of which is to leverage the sparsity occurring in deep neural networks due to the high levels of redundancy in the network parameters.
TensorQuant - A Simulation Toolbox for Deep Neural Network Quantization
While most related publications validate the proposed approach on a single DNN topology, it appears to be evident, that the optimal choice of the quantization method and number of coding bits is topology dependent.
Facies classification from well logs using an inception convolutional network
The idea to use automated algorithms to determine geological facies from well logs is not new (see e. g Busch et al. (1987); Rabaute (1998)) but the recent and dramatic increase in research in the field of machine learning makes it a good time to revisit the topic.
Using GPI-2 for Distributed Memory Paralleliziation of the Caffe Toolbox to Speed up Deep Neural Network Training
I/O is an other bottleneck to work with DDNs in a standard parallel HPC setting, which we will consider in more detail in a forthcoming paper.
Distributed Training of Deep Neural Networks: Theoretical and Practical Limits of Parallel Scalability
This paper presents a theoretical analysis and practical evaluation of the main bottlenecks towards a scalable distributed solution for the training of Deep Neuronal Networks (DNNs).
Asynchronous Parallel Stochastic Gradient Descent - A Numeric Core for Scalable Distributed Machine Learning Algorithms
In this context, Stochastic Gradient Descent (SGD) methods have long proven to provide good results, both in terms of convergence and accuracy.
Distributed, Parallel, and Cluster Computing
