765 citations · 3.7k across the 105 of their papers we have counts for
68 papers · 1 filter
B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers
Moritz Böhle, Navdeeppal Singh, Mario Fritz +1
We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training. For this, we propose to replace t…
Holistically Explainable Vision Transformers
Moritz Böhle, Mario Fritz, Bernt Schiele
Transformers increasingly dominate the machine learning landscape across many tasks and domains, which increases the importance for understanding their outputs. While their attenti…
B-cos Networks: Alignment is All We Need for Interpretability
Moritz Böhle, Mario Fritz, Bernt Schiele
We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training. For this, we propose to replace t…
Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources
Sahar Abdelnabi, Rakibul Hasan, Mario Fritz
Misinformation is now a major problem due to its potential high risks to our core democratic and societal values and orders. Out-of-context misinformation is one of the easiest and…
Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers
Apratim Bhattacharyya, Daniel Olmeda Reino, Mario Fritz +1
Accurate prediction of pedestrian and bicyclist paths is integral to the development of reliable autonomous vehicles in dense urban environments. The interactions between vehicle a…
Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis
Yang He, Ning Yu, Margret Keuper +1
The rapid advances in deep generative models over the past years have led to highly {realistic media, known as deepfakes,} that are commonly indistinguishable from real to human ey…
Dual Contrastive Loss and Attention for GANs
Ning Yu, Guilin Liu, Aysegul Dundar +4
Generative Adversarial Networks (GANs) produce impressive results on unconditional image generation when powered with large-scale image datasets. Yet generated images are still eas…
Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs
Hui-Po Wang, Ning Yu, Mario Fritz
While Generative Adversarial Networks (GANs) show increasing performance and the level of realism is becoming indistinguishable from natural images, this also comes with high deman…
Haar Wavelet based Block Autoregressive Flows for Trajectories
Apratim Bhattacharyya, Christoph-Nikolas Straehle, Mario Fritz +1
Prediction of trajectories such as that of pedestrians is crucial to the performance of autonomous agents. While previous works have leveraged conditional generative models like GA…
Synthetic Convolutional Features for Improved Semantic Segmentation
Yang He, Bernt Schiele, Mario Fritz
Recently, learning-based image synthesis has enabled to generate high-resolution images, either applying popular adversarial training or a powerful perceptual loss. However, it rem…
InfoScrub: Towards Attribute Privacy by Targeted Obfuscation
Hui-Po Wang, Tribhuvanesh Orekondy, Mario Fritz
Personal photos of individuals when shared online, apart from exhibiting a myriad of memorable details, also reveals a wide range of private information and potentially entails pri…
Long-Tailed Recognition Using Class-Balanced Experts
Saurabh Sharma, Ning Yu, Mario Fritz +1
Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced dis…
Inclusive GAN: Improving Data and Minority Coverage in Generative Models
Ning Yu, Ke Li, Peng Zhou +3
Generative Adversarial Networks (GANs) have brought about rapid progress towards generating photorealistic images. Yet the equitable allocation of their modeling capacity among sub…
Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation
Yang He, Shadi Rahimian, Bernt Schiele +1
Today's success of state of the art methods for semantic segmentation is driven by large datasets. Data is considered an important asset that needs to be protected, as the collecti…
Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing
Vedika Agarwal, Rakshith Shetty, Mario Fritz
Despite significant success in Visual Question Answering (VQA), VQA models have been shown to be notoriously brittle to linguistic variations in the questions. Due to deficiencies…
Conditional Flow Variational Autoencoders for Structured Sequence Prediction
Apratim Bhattacharyya, Michael Hanselmann, Mario Fritz +2
Prediction of future states of the environment and interacting agents is a key competence required for autonomous agents to operate successfully in the real world. Prior work for s…
Interpretability Beyond Classification Output: Semantic Bottleneck Networks
Max Losch, Mario Fritz, Bernt Schiele
Today's deep learning systems deliver high performance based on end-to-end training. While they deliver strong performance, these systems are hard to interpret. To address this iss…
Body Shape Privacy in Images: Understanding Privacy and Preventing Automatic Shape Extraction
Hosnieh Sattar, Katharina Krombholz, Gerard Pons-Moll +1
Modern approaches to pose and body shape estimation have recently achieved strong performance even under challenging real-world conditions. Even from a single image of a clothed pe…
Not Using the Car to See the Sidewalk: Quantifying and Controlling the Effects of Context in Classification and Segmentation
Rakshith Shetty, Bernt Schiele, Mario Fritz
Importance of visual context in scene understanding tasks is well recognized in the computer vision community. However, to what extent the computer vision models for image classifi…
Knockoff Nets: Stealing Functionality of Black-Box Models
Tribhuvanesh Orekondy, Bernt Schiele, Mario Fritz
Machine Learning (ML) models are increasingly deployed in the wild to perform a wide range of tasks. In this work, we ask to what extent can an adversary steal functionality of suc…
Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
Ning Yu, Larry Davis, Mario Fritz
Recent advances in Generative Adversarial Networks (GANs) have shown increasing success in generating photorealistic images. But they also raise challenges to visual forensics and…
Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods
Apratim Bhattacharyya, Mario Fritz, Bernt Schiele
For autonomous agents to successfully operate in the real world, the ability to anticipate future scene states is a key competence. In real-world scenarios, future states become in…
Answering Visual What-If Questions: From Actions to Predicted Scene Descriptions
M. Wagner, H. Basevi, R. Shetty +4
In-depth scene descriptions and question answering tasks have greatly increased the scope of today's definition of scene understanding. While such tasks are in principle open ended…
Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes
Yang He, Bernt Schiele, Mario Fritz
Recent advances in Deep Learning and probabilistic modeling have led to strong improvements in generative models for images. On the one hand, Generative Adversarial Networks (GANs)…