Official Implementation of the paper "A U-Net Based Discriminator for Generative Adversarial Networks" (CVPR 2020)

Official implementation of the paper "You Only Need Adversarial Supervision for Semantic Image Synthesis" (ICLR 2021)

Source code for Fathony, Sahu, Willmott, & Kolter, "Multiplicative Filter Networks", ICLR 2021.

[CVPR 2024] Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships

Resources related to EACL 2023 paper "SwitchPrompt: Learning Domain-Specific Gated Soft Prompts for Classification in Low-Resource Domains"

Python implementation of the PR-SSM.

[DEPRECATED] Procedural generation library for Gazebo (please refer to https://github.com/boschresearch/pcg_gazebo)

Implementation of the paper "Understanding anomaly detection with deep invertible networks through hierarchies of distributions and features" (NeurIPS 2020)

Official PyTorch implementation of the paper "Generating Novel Scene Compositions from Single Images and Videos"

Coder of the paper 'Latent Outlier Exposure for Anomaly Detectin with Contaminated Data' published in ICML 2022

Code of the paper 'Neural Transformation Learning for Anomaly Detection' published in ICML 2021

Code accompanying Coling2020 publication on data augmentation for named entity recognition

Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization

Official Implementation of the paper "Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation" (ECCV 2022)

Supplementary source code for the ECRTS 2019 paper 'Response-Time Analysis of ROS 2 Processing Chains under Reservation-Based Scheduling'

Code base for physics-based photorealistic rendering within the scope of Bosch BCAI AMIRA probject

Tensorflow implementation of Meta Adversarial Training for Adversarial Patch Attacks on Tiny ImageNet.

This is the code accompanying the AAAI 2022 paper "Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives" https://arxiv.org/abs/2201.11736 . The method allows you to use additional ranking information for representation learning.