2.6k citations · 9.3k across the 89 of their papers we have counts for
15 papers · 1 filter
Search for temporal cell segmentation robustness in phase-contrast microscopy videos
Estibaliz Gómez-de-Mariscal, Hasini Jayatilaka, Özgün Çiçek +3
Studying cell morphology changes in time is critical to understanding cell migration mechanisms. In this work, we present a deep learning-based workflow to segment cancer cells emb…
You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction
Osama Makansi, Julius von Kügelgen, Francesco Locatello +4
Predicting the future trajectory of a moving agent can be easy when the past trajectory continues smoothly but is challenging when complex interactions with other agents are involv…
Unsupervised Object Learning via Common Fate
Matthias Tangemann, Steffen Schneider, Julius von Kügelgen +6
Learning generative object models from unlabelled videos is a long standing problem and required for causal scene modeling. We decompose this problem into three easier subtasks, an…
CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations
Mohammadreza Zolfaghari, Yi Zhu, Peter Gehler +1
Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn c…
Multi-headed Neural Ensemble Search
Ashwin Raaghav Narayanan, Arber Zela, Tonmoy Saikia +2
Ensembles of CNN models trained with different seeds (also known as Deep Ensembles) are known to achieve superior performance over a single copy of the CNN. Neural Ensemble Search…
Contrastive Representation Learning for Hand Shape Estimation
Christian Zimmermann, Max Argus, Thomas Brox
This work presents improvements in monocular hand shape estimation by building on top of recent advances in unsupervised learning. We extend momentum contrastive learning and contr…
Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
Chaithanya Kumar Mummadi, Robin Hutmacher, Kilian Rambach +3
Deep neural networks often exhibit poor performance on data that is unlikely under the train-time data distribution, for instance data affected by corruptions. Previous works demon…
Towards Total Recall in Industrial Anomaly Detection
Karsten Roth, Latha Pemula, Joaquin Zepeda +3
Being able to spot defective parts is a critical component in large-scale industrial manufacturing. A particular challenge that we address in this work is the cold-start problem: f…
Semi-Supervised Disparity Estimation with Deep Feature Reconstruction
Julia Guerrero-Viu, Sergio Izquierdo, Philipp Schröppel +1
Despite the success of deep learning in disparity estimation, the domain generalization gap remains an issue. We propose a semi-supervised pipeline that successfully adapts DispNet…
Pre-training of Deep RL Agents for Improved Learning under Domain Randomization
Artemij Amiranashvili, Max Argus, Lukas Hermann +2
Visual domain randomization in simulated environments is a widely used method to transfer policies trained in simulation to real robots. However, domain randomization and augmentat…
Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors
Jan Bechtold, Maxim Tatarchenko, Volker Fischer +1
Single-view 3D object reconstruction has seen much progress, yet methods still struggle generalizing to novel shapes unseen during training. Common approaches predominantly rely on…
Improving robustness against common corruptions with frequency biased models
Tonmoy Saikia, Cordelia Schmid, Thomas Brox
CNNs perform remarkably well when the training and test distributions are i.i.d, but unseen image corruptions can cause a surprisingly large drop in performance. In various real sc…
Towards Understanding Adversarial Robustness of Optical Flow Networks
Simon Schrodi, Tonmoy Saikia, Thomas Brox
Recent work demonstrated the lack of robustness of optical flow networks to physical patch-based adversarial attacks. The possibility to physically attack a basic component of auto…
On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors
Osama Makansi, Özgün Cicek, Yassine Marrakchi +1
Predicting the states of dynamic traffic actors into the future is important for autonomous systems to operate safelyand efficiently. Remarkably, the most critical scenarios aremuc…
Essentials for Class Incremental Learning
Sudhanshu Mittal, Silvio Galesso, Thomas Brox
Contemporary neural networks are limited in their ability to learn from evolving streams of training data. When trained sequentially on new or evolving tasks, their accuracy drops…