Search Results for author: Thomas Breuel

Found 15 papers, 6 papers with code

Investigating the Nature of 3D Generalization in Deep Neural Networks

1 code implementation19 Apr 2023 Shoaib Ahmed Siddiqui, David Krueger, Thomas Breuel

Modern deep learning architectures for object recognition generalize well to novel views, but the mechanisms are not well understood.

Object Recognition

GroupViT: Semantic Segmentation Emerges from Text Supervision

2 code implementations CVPR 2022 Jiarui Xu, Shalini De Mello, Sifei Liu, Wonmin Byeon, Thomas Breuel, Jan Kautz, Xiaolong Wang

With only text supervision and without any pixel-level annotations, GroupViT learns to group together semantic regions and successfully transfers to the task of semantic segmentation in a zero-shot manner, i. e., without any further fine-tuning.

Object Detection Scene Understanding +3

Identifying Layers Susceptible to Adversarial Attacks

no code implementations10 Jul 2021 Shoaib Ahmed Siddiqui, Thomas Breuel

In this paper, we investigate the use of pretraining with adversarial networks, with the objective of discovering the relationship between network depth and robustness.

Dimensionality Reduction

ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning

1 code implementation ICCV 2021 Sangho Lee, Jiwan Chung, Youngjae Yu, Gunhee Kim, Thomas Breuel, Gal Chechik, Yale Song

We demonstrate that our approach finds videos with high audio-visual correspondence and show that self-supervised models trained on our data achieve competitive performances compared to models trained on existing manually curated datasets.

Representation Learning

Parameter Efficient Multimodal Transformers for Video Representation Learning

no code implementations ICLR 2021 Sangho Lee, Youngjae Yu, Gunhee Kim, Thomas Breuel, Jan Kautz, Yale Song

The recent success of Transformers in the language domain has motivated adapting it to a multimodal setting, where a new visual model is trained in tandem with an already pretrained language model.

Language Modelling Representation Learning

Discovering Nonlinear Relations with Minimum Predictive Information Regularization

1 code implementation7 Jan 2020 Tailin Wu, Thomas Breuel, Michael Skuhersky, Jan Kautz

Identifying the underlying directional relations from observational time series with nonlinear interactions and complex relational structures is key to a wide range of applications, yet remains a hard problem.

Time Series Time Series Analysis

Neural Causal Discovery with Learnable Input Noise

no code implementations ICLR 2019 Tailin Wu, Thomas Breuel, Jan Kautz

Learning causal relations from observational time series with nonlinear interactions and complex causal structures is a key component of human intelligence, and has a wide range of applications.

Causal Discovery EEG +3

Unsupervised Image-to-Image Translation Networks

8 code implementations NeurIPS 2017 Ming-Yu Liu, Thomas Breuel, Jan Kautz

Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains.

Domain Adaptation Multimodal Unsupervised Image-To-Image Translation +2

Sequence-to-sequence neural network models for transliteration

1 code implementation29 Oct 2016 Mihaela Rosca, Thomas Breuel

Transliteration is a key component of machine translation systems and software internationalization.

Translation Transliteration

Efficient Estimation of k for the Nearest Neighbors Class of Methods

no code implementations8 Jun 2016 Aleksander Lodwich, Faisal Shafait, Thomas Breuel

From countless experiments of the past it became widely accepted that the value of k has a significant impact on the performance of this method.

Cannot find the paper you are looking for? You can Submit a new open access paper.