107 citations · 211 across the 14 of their papers we have counts for
17 papers
Fin-Fed-OD: Federated Outlier Detection on Financial Tabular Data
Dayananda Herurkar, Sebastian Palacio, Ahmed Anwar +2
Anomaly detection in real-world scenarios poses challenges due to dynamic and often unknown anomaly distributions, requiring robust methods that operate under an open-world assumpt…
ObjBlur: A Curriculum Learning Approach With Progressive Object-Level Blurring for Improved Layout-to-Image Generation
Stanislav Frolov, Brian B. Moser, Sebastian Palacio +1
We present ObjBlur, a novel curriculum learning approach to improve layout-to-image generation models, where the task is to produce realistic images from layouts composed of boxes…
Unlocking Dataset Distillation with Diffusion Models
Brian B. Moser, Federico Raue, Sebastian Palacio +2
Dataset distillation seeks to condense datasets into smaller but highly representative synthetic samples. While diffusion models now lead all generative benchmarks, current distill…
TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax
Tobias Christian Nauen, Sebastian Palacio, Andreas Dengel
The quadratic complexity of the attention mechanism represents one of the biggest hurdles for processing long sequences using Transformers. Current methods, relying on sparse repre…
Diffusion Models, Image Super-Resolution And Everything: A Survey
Brian B. Moser, Arundhati S. Shanbhag, Federico Raue +3
Diffusion Models (DMs) have disrupted the image Super-Resolution (SR) field and further closed the gap between image quality and human perceptual preferences. They are easy to trai…
Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers
Tobias Christian Nauen, Sebastian Palacio, Federico Raue +1
Self-attention in Transformers comes with a high computational cost because of their quadratic computational complexity, but their effectiveness in addressing problems in language…
Dynamic Attention-Guided Diffusion for Image Super-Resolution
Brian B. Moser, Stanislav Frolov, Federico Raue +2
Diffusion models in image Super-Resolution (SR) treat all image regions uniformly, which risks compromising the overall image quality by potentially introducing artifacts during de…
DWA: Differential Wavelet Amplifier for Image Super-Resolution
Brian B. Moser, Stanislav Frolov, Federico Raue +2
This work introduces Differential Wavelet Amplifier (DWA), a drop-in module for wavelet-based image Super-Resolution (SR). DWA invigorates an approach recently receiving less atten…
Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolution
Brian Moser, Stanislav Frolov, Federico Raue +2
This paper presents a novel Diffusion-Wavelet (DiWa) approach for Single-Image Super-Resolution (SISR). It leverages the strengths of Denoising Diffusion Probabilistic Models (DDPM…
Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
Brian Moser, Federico Raue, Stanislav Frolov +3
With the advent of Deep Learning (DL), Super-Resolution (SR) has also become a thriving research area. However, despite promising results, the field still faces challenges that req…
Spatial Transformer Networks for Curriculum Learning
Fatemeh Azimi, Jean-Francois Jacques Nicolas Nies, Sebastian Palacio +3
Curriculum learning is a bio-inspired training technique that is widely adopted to machine learning for improved optimization and better training of neural networks regarding the c…
XAI Handbook: Towards a Unified Framework for Explainable AI
Sebastian Palacio, Adriano Lucieri, Mohsin Munir +3
The field of explainable AI (XAI) has quickly become a thriving and prolific community. However, a silent, recurrent and acknowledged issue in this area is the lack of consensus re…
Contextual Classification Using Self-Supervised Auxiliary Models for Deep Neural Networks
Sebastian Palacio, Philipp Engler, Jörn Hees +1
Classification problems solved with deep neural networks (DNNs) typically rely on a closed world paradigm, and optimize over a single objective (e.g., minimization of the cross-ent…
Revisiting Sequence-to-Sequence Video Object Segmentation with Multi-Task Loss and Skip-Memory
Fatemeh Azimi, Benjamin Bischke, Sebastian Palacio +3
Video Object Segmentation (VOS) is an active research area of the visual domain. One of its fundamental sub-tasks is semi-supervised / one-shot learning: given only the segmentatio…
P NP, at least in Visual Question Answering
Shailza Jolly, Sebastian Palacio, Joachim Folz +3
In recent years, progress in the Visual Question Answering (VQA) field has largely been driven by public challenges and large datasets. One of the most widely-used of these is the…
What do Deep Networks Like to See?
Sebastian Palacio, Joachim Folz, Jörn Hees +3
We propose a novel way to measure and understand convolutional neural networks by quantifying the amount of input signal they let in. To do this, an autoencoder (AE) was fine-tuned…
Adversarial Defense based on Structure-to-Signal Autoencoders
Joachim Folz, Sebastian Palacio, Joern Hees +2
Adversarial attack methods have demonstrated the fragility of deep neural networks. Their imperceptible perturbations are frequently able fool classifiers into potentially dangerou…