Zobrazeno 1 - 10
of 1 317
pro vyhledávání: '"Keuper, A."'
Not all learnable parameters (e.g., weights) contribute equally to a neural network's decision function. In fact, entire layers' parameters can sometimes be reset to random values with little to no impact on the model's decisions. We revisit earlier
Externí odkaz:
http://arxiv.org/abs/2410.14470
In this paper, we present an approach for evaluating attribution maps, which play a central role in interpreting the predictions of convolutional neural networks (CNNs). We show that the widely used insertion/deletion metrics are susceptible to distr
Externí odkaz:
http://arxiv.org/abs/2411.14946
Autor:
Nieradzik, Lars, Stephani, Henrike, Sieburg-Rockel, Jördis, Helmling, Stephanie, Olbrich, Andrea, Wrage, Stephanie, Keuper, Janis
Wood species identification plays a crucial role in various industries, from ensuring the legality of timber products to advancing ecological conservation efforts. This paper introduces WoodYOLO, a novel object detection algorithm specifically design
Externí odkaz:
http://arxiv.org/abs/2411.11738
Deep neural networks are susceptible to adversarial attacks and common corruptions, which undermine their robustness. In order to enhance model resilience against such challenges, Adversarial Training (AT) has emerged as a prominent solution. Neverth
Externí odkaz:
http://arxiv.org/abs/2410.23142
This paper introduces Top-GAP, a novel regularization technique that enhances the explainability and robustness of convolutional neural networks. By constraining the spatial size of the learned feature representation, our method forces the network to
Externí odkaz:
http://arxiv.org/abs/2409.04819
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. Data aggregation as well as high-resolution ima
Externí odkaz:
http://arxiv.org/abs/2406.07435
Autor:
Lamm, Bianca, Keuper, Janis
Most production-level deployments for Visual Question Answering (VQA) tasks are still build as processing pipelines of independent steps including image pre-processing, object- and text detection, Optical Character Recognition (OCR) and (mostly super
Externí odkaz:
http://arxiv.org/abs/2408.15626
Sampling-based decoding strategies have been widely adopted for Large Language Models (LLMs) in numerous applications, which target a balance between diversity and quality via temperature tuning and tail truncation (e.g., top-k and top-p sampling). C
Externí odkaz:
http://arxiv.org/abs/2408.13586
Foundation models (FMs) have revolutionized computer vision, enabling effective learning across different domains. However, their performance under domain shift is yet underexplored. This paper investigates the zero-shot domain adaptation potential o
Externí odkaz:
http://arxiv.org/abs/2407.03482
SoftMax is a ubiquitous ingredient of modern machine learning algorithms. It maps an input vector onto a probability simplex and reweights the input by concentrating the probability mass at large entries. Yet, as a smooth approximation to the Argmax
Externí odkaz:
http://arxiv.org/abs/2406.01189