2.1k citations · 5.7k across the 61 of their papers we have counts for
22 papers · 1 filter
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
Andreas Hochlehnert, Marianna Nezhurina, Mehdi Cherti +9
We present LAION-BVD, a large-scale open video dataset for multimodal learning, which contains 1.3B platform-specific video URLs collected from CommonCrawl. From these, we download…
Is Generation Required for Data-Efficient Perception?
Jack Brady, Bernhard Schölkopf, Thomas Kipf +2
It has been hypothesized that achieving the data efficiency of human visual perception requires a generative approach in which internal representations result from inverting a deco…
In Search of Forgotten Domain Generalization
Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer +4
Out-of-Domain (OOD) generalization is the ability of a model trained on one or more domains to generalize to unseen domains. In the ImageNet era of computer vision, evaluation sets…
Effective pruning of web-scale datasets based on complexity of concept clusters
Amro Abbas, Evgenia Rusak, Kushal Tirumala +3
Utilizing massive web-scale datasets has led to unprecedented performance gains in machine learning models, but also imposes outlandish compute requirements for their training. In…
Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?
Prasanna Mayilvahanan, Thaddäus Wiedemer, Evgenia Rusak +2
Foundation models like CLIP are trained on hundreds of millions of samples and effortlessly generalize to new tasks and inputs. Out of the box, CLIP shows stellar zero-shot and few…
Scale Alone Does not Improve Mechanistic Interpretability in Vision Models
Roland S. Zimmermann, Thomas Klein, Wieland Brendel
In light of the recent widespread adoption of AI systems, understanding the internal information processing of neural networks has become increasingly critical. Most recently, mach…
Don't trust your eyes: on the (un)reliability of feature visualizations
Robert Geirhos, Roland S. Zimmermann, Blair Bilodeau +2
How do neural networks extract patterns from pixels? Feature visualizations attempt to answer this important question by visualizing highly activating patterns through optimization…
How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
Roland S. Zimmermann, Judy Borowski, Robert Geirhos +3
A precise understanding of why units in an artificial network respond to certain stimuli would constitute a big step towards explainable artificial intelligence. One widely used ap…
Partial success in closing the gap between human and machine vision
Robert Geirhos, Kantharaju Narayanappa, Benjamin Mitzkus +4
A few years ago, the first CNN surpassed human performance on ImageNet. However, it soon became clear that machines lack robustness on more challenging test cases, a major obstacle…
If your data distribution shifts, use self-learning
Evgenia Rusak, Steffen Schneider, George Pachitariu +5
We demonstrate that self-learning techniques like entropy minimization and pseudo-labeling are simple and effective at improving performance of a deployed computer vision model und…
On the surprising similarities between supervised and self-supervised models
Robert Geirhos, Kantharaju Narayanappa, Benjamin Mitzkus +3
How do humans learn to acquire a powerful, flexible and robust representation of objects? While much of this process remains unknown, it is clear that humans do not require million…
Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization
Judy Borowski, Roland S. Zimmermann, Judith Schepers +4
Feature visualizations such as synthetic maximally activating images are a widely used explanation method to better understand the information processing of convolutional neural ne…
Benchmarking Unsupervised Object Representations for Video Sequences
Marissa A. Weis, Kashyap Chitta, Yash Sharma +4
Perceiving the world in terms of objects and tracking them through time is a crucial prerequisite for reasoning and scene understanding. Recently, several methods have been propose…
Five Points to Check when Comparing Visual Perception in Humans and Machines
Christina M. Funke, Judy Borowski, Karolina Stosio +3
With the rise of machines to human-level performance in complex recognition tasks, a growing amount of work is directed towards comparing information processing in humans and machi…
Shortcut Learning in Deep Neural Networks
Robert Geirhos, Jörn-Henrik Jacobsen, Claudio Michaelis +4
Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today's machine intelligence. Numerous success stories have rapidly spread all over…
A simple way to make neural networks robust against diverse image corruptions
Evgenia Rusak, Lukas Schott, Roland S. Zimmermann +4
The human visual system is remarkably robust against a wide range of naturally occurring variations and corruptions like rain or snow. In contrast, the performance of modern image…
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
Claudio Michaelis, Benjamin Mitzkus, Robert Geirhos +5
The ability to detect objects regardless of image distortions or weather conditions is crucial for real-world applications of deep learning like autonomous driving. We here provide…
Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet
Wieland Brendel, Matthias Bethge
Deep Neural Networks (DNNs) excel on many complex perceptual tasks but it has proven notoriously difficult to understand how they reach their decisions. We here introduce a high-pe…
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
Robert Geirhos, Patricia Rubisch, Claudio Michaelis +3
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes. Some recent studies suggest a more…
One-shot Texture Segmentation
Ivan Ustyuzhaninov, Claudio Michaelis, Wieland Brendel +1
We introduce one-shot texture segmentation: the task of segmenting an input image containing multiple textures given a patch of a reference texture. This task is designed to turn t…
Towards the first adversarially robust neural network model on MNIST
Lukas Schott, Jonas Rauber, Matthias Bethge +1
Despite much effort, deep neural networks remain highly susceptible to tiny input perturbations and even for MNIST, one of the most common toy datasets in computer vision, no neura…
Texture Synthesis Using Shallow Convolutional Networks with Random Filters
Ivan Ustyuzhaninov, Wieland Brendel, Leon A. Gatys +1
Here we demonstrate that the feature space of random shallow convolutional neural networks (CNNs) can serve as a surprisingly good model of natural textures. Patches from the same…