70 citations · 154 across the 14 of their papers we have counts for
14 papers
Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization
Yumeng Li, Dan Zhang, Margret Keuper +1
The generalization with respect to domain shifts, as they frequently appear in applications such as autonomous driving, is one of the remaining big challenges for deep learning mod…
High Dynamic Range Imaging with Context-aware Transformer
Fangfang Zhou, Dan Zhang, Zhenming Fu
Avoiding the introduction of ghosts when synthesising LDR images as high dynamic range (HDR) images is a challenging task. Convolutional neural networks (CNNs) are effective for HD…
Learning From Yourself: A Self-Distillation Method for Fake Speech Detection
Jun Xue, Cunhang Fan, Jiangyan Yi +4
In this paper, we propose a novel self-distillation method for fake speech detection (FSD), which can significantly improve the performance of FSD without increasing the model comp…
GOOD: Exploring Geometric Cues for Detecting Objects in an Open World
Haiwen Huang, Andreas Geiger, Dan Zhang
We address the task of open-world class-agnostic object detection, i.e., detecting every object in an image by learning from a limited number of base object classes. State-of-the-a…
Intra-Source Style Augmentation for Improved Domain Generalization
Yumeng Li, Dan Zhang, Margret Keuper +1
The generalization with respect to domain shifts, as they frequently appear in applications such as autonomous driving, is one of the remaining big challenges for deep learning mod…
One-Shot Synthesis of Images and Segmentation Masks
Vadim Sushko, Dan Zhang, Juergen Gall +1
Joint synthesis of images and segmentation masks with generative adversarial networks (GANs) is promising to reduce the effort needed for collecting image data with pixel-wise anno…
BridgeNet: A Joint Learning Network of Depth Map Super-Resolution and Monocular Depth Estimation
Qi Tang, Runmin Cong, Ronghui Sheng +4
Depth map super-resolution is a task with high practical application requirements in the industry. Existing color-guided depth map super-resolution methods usually necessitate an e…
Generating Novel Scene Compositions from Single Images and Videos
Vadim Sushko, Dan Zhang, Juergen Gall +1
Given a large dataset for training, generative adversarial networks (GANs) can achieve remarkable performance for the image synthesis task. However, training GANs in extremely low…
You Only Need Adversarial Supervision for Semantic Image Synthesis
Vadim Sushko, Edgar Schönfeld, Dan Zhang +3
Despite their recent successes, GAN models for semantic image synthesis still suffer from poor image quality when trained with only adversarial supervision. Historically, additiona…
Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning
Kanil Patel, William Beluch, Bin Yang +2
Post-hoc multi-class calibration is a common approach for providing high-quality confidence estimates of deep neural network predictions. Recent work has shown that widely used sca…
Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features
Robin Tibor Schirrmeister, Yuxuan Zhou, Tonio Ball +1
Deep generative networks trained via maximum likelihood on a natural image dataset like CIFAR10 often assign high likelihoods to images from datasets with different objects (e.g.,…
On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration
Kanil Patel, William Beluch, Dan Zhang +2
Uncertainty estimates help to identify ambiguous, novel, or anomalous inputs, but the reliable quantification of uncertainty has proven to be challenging for modern deep networks.…
Group Pruning using a Bounded-Lp norm for Group Gating and Regularization
Chaithanya Kumar Mummadi, Tim Genewein, Dan Zhang +2
Deep neural networks achieve state-of-the-art results on several tasks while increasing in complexity. It has been shown that neural networks can be pruned during training by impos…
Progressive Augmentation of GANs
Dan Zhang, Anna Khoreva
Training of Generative Adversarial Networks (GANs) is notoriously fragile, requiring to maintain a careful balance between the generator and the discriminator in order to perform w…