Search Results for author:
Found 13 papers, 6 papers with code
Scale Alone Does not Improve Mechanistic Interpretability in Vision Models
We use a psychophysical paradigm to quantify one form of mechanistic interpretability for a diverse suite of nine models and find no scaling effect for interpretability - neither for model nor dataset size.
Don't trust your eyes: on the (un)reliability of feature visualizations
Today, visualization methods form the foundation of our knowledge about the internal workings of neural networks, as a type of mechanistic interpretability.
Sensitivity of Slot-Based Object-Centric Models to their Number of Slots
Self-supervised methods for learning object-centric representations have recently been applied successfully to various datasets.
Provably Learning Object-Centric Representations
Under this generative process, we prove that the ground-truth object representations can be identified by an invertible and compositional inference model, even in the presence of dependencies between objects.
Increasing Confidence in Adversarial Robustness Evaluations
Hundreds of defenses have been proposed to make deep neural networks robust against minimal (adversarial) input perturbations.
Score-Based Generative Classifiers
In this work, we investigate score-based generative models as classifiers for natural images.
How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
A precise understanding of why units in an artificial network respond to certain stimuli would constitute a big step towards explainable artificial intelligence.
Contrastive Learning Inverts the Data Generating Process
Contrastive learning has recently seen tremendous success in self-supervised learning.
Ranked #1 on
Disentanglement
on KITTI-Masks
Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization
Even if only a single reference image is given, synthetic images provide less information than natural images ($65\pm5\%$ vs. $73\pm4\%$).
A simple way to make neural networks robust against diverse image corruptions
The human visual system is remarkably robust against a wide range of naturally occurring variations and corruptions like rain or snow.
Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"
A recent paper by Liu et al. combines the topics of adversarial training and Bayesian Neural Networks (BNN) and suggests that adversarially trained BNNs are more robust against adversarial attacks than their non-Bayesian counterparts.
Simion Zoo: A Workbench for Distributed Experimentation with Reinforcement Learning for Continuous Control Tasks
We present Simion Zoo, a Reinforcement Learning (RL) workbench that provides a complete set of tools to design, run, and analyze the results, both statistically and visually, of RL control applications.
Faster Training of Mask R-CNN by Focusing on Instance Boundaries
We present an auxiliary task to Mask R-CNN, an instance segmentation network, which leads to faster training of the mask head.
