Search Results for author:
Found 22 papers, 8 papers with code
Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Representation Learning
This revealed that the driving factor behind both, the modality gap and the object bias, is the information imbalance between images and captions.
Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
In this work, we study rapid, step-wise improvements of the loss in transformers when being confronted with multi-step decision tasks.
Zero-Shot Visual Classification with Guided Cropping
We empirically show that our approach improves zero-shot classification results across architectures and datasets, favorably for small objects.
Multi-Attribute Open Set Recognition
While conventional OSR approaches can detect Out-of-Distribution (OOD) samples, they cannot provide explanations indicating which underlying visual attribute(s) (e. g., shape, color or background) cause a specific sample to be unknown.
Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain
Our approach extends the training set with an additional dataset (the source domain), which is specifically designed to facilitate learning independent representations of basic visual factors.
Contrasting quadratic assignments for set-based representation learning
The views are ordered in pairs, such that they are either positive, encoding different views of the same object, or negative, corresponding to views of different objects.
DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunities
We also argue that it is necessary for DNNs to exploit GO to overcome shortcut learning.
EML Online Speech Activity Detection for the Fearless Steps Challenge Phase-III
Speech Activity Detection (SAD), locating speech segments within an audio recording, is a main part of most speech technology applications.
Does enhanced shape bias improve neural network robustness to common corruptions?
We conclude that the data augmentation caused by style-variation accounts for the improved corruption robustness and increased shape bias is only a byproduct.
Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors
Single-view 3D object reconstruction has seen much progress, yet methods still struggle generalizing to novel shapes unseen during training.
EML System Description for VoxCeleb Speaker Diarization Challenge 2020
This technical report describes the EML submission to the first VoxCeleb speaker diarization challenge.
SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks
We introduce the SE(3)-Transformer, a variant of the self-attention module for 3D point clouds and graphs, which is equivariant under continuous 3D roto-translations.
Group Pruning using a Bounded-Lp norm for Group Gating and Regularization
We achieve state-of-the-art pruning results for ResNet-50 with higher accuracy on ImageNet.
Grid Saliency for Context Explanations of Semantic Segmentation
Recently, there has been a growing interest in developing saliency methods that provide visual explanations of network predictions.
Short-Term Prediction and Multi-Camera Fusion on Semantic Grids
An environment representation (ER) is a substantial part of every autonomous system.
Functionally Modular and Interpretable Temporal Filtering for Robust Segmentation
Our filter module splits the filter task into multiple less complex and more interpretable subtasks.
Hierarchical Recurrent Filtering for Fully Convolutional DenseNets
Generating a robust representation of the environment is a crucial ability of learning agents.
The streaming rollout of deep networks - towards fully model-parallel execution
Deep neural networks, and in particular recurrent networks, are promising candidates to control autonomous agents that interact in real-time with the physical world.
Statestream: A toolbox to explore layerwise-parallel deep neural networks
Most artificial deep neural networks are partitioned into a directed graph of connected modules or layers and the layers themselves consist of elemental building blocks, such as single units.
Universal Adversarial Perturbations Against Semantic Image Segmentation
We show empirically that there exist barely perceptible universal noise patterns which result in nearly the same predicted segmentation for arbitrary inputs.
Adversarial Examples for Semantic Image Segmentation
Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations.
On Detecting Adversarial Perturbations
In this work, we propose to augment deep neural networks with a small "detector" subnetwork which is trained on the binary classification task of distinguishing genuine data from data containing adversarial perturbations.
