Search Results for author:
Found 26 papers, 19 papers with code
Aligning Machine and Human Visual Representations across Abstraction Levels
Deep neural networks have achieved success across a wide range of applications, including as models of human behavior in vision tasks.
PaliGemma: A versatile 3B VLM for transfer
PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m vision encoder and the Gemma-2B language model.
Getting aligned on representational alignment
Finally, we lay out open problems in representational alignment where progress can benefit all three of these fields.
Set Learning for Accurate and Calibrated Models
Model overconfidence and poor calibration are common in machine learning and difficult to account for when applying standard empirical risk minimization.
Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations
Molecular dynamics (MD) simulations allow atomistic insights into chemical and biological processes.
GradMax: Growing Neural Networks using Gradient Information
The architecture and the parameters of neural networks are often optimized independently, which requires costly retraining of the parameters whenever the architecture is modified.
Do Vision Transformers See Like Convolutional Neural Networks?
Finally, we study the effect of (pretraining) dataset scale on intermediate features and transfer learning, and conclude with a discussion on connections to new architectures such as the MLP-Mixer.
MLP-Mixer: An all-MLP Architecture for Vision
Convolutional Neural Networks (CNNs) are the go-to model for computer vision.
Ranked #17 on
Image Classification
on OmniBenchmark
Differentiable Patch Selection for Image Recognition
Neural Networks require large amounts of memory and compute to process high resolution images, even when only a small part of the image is actually informative for the task at hand.
Understanding Robustness of Transformers for Image Classification
We find that when pre-trained with a sufficient amount of data, ViT models are at least as robust as the ResNet counterparts on a broad range of perturbations.
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
(Carton Gap metric)
Object-Centric Learning with Slot Attention
Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features.
Predicting Neural Network Accuracy from Weights
Furthermore, the predictors are able to rank networks trained on different, unobserved datasets and with different architectures.
FVD: A new Metric for Video Generation
While recent generative models of video have had some success, current progress is hampered by the lack of qualitative metrics that consider visual quality, temporal coherence, and diversity of samples.
Interpretable Deep Learning in Drug Discovery
Without any means of interpretation, neural networks that predict molecular properties and bioactivities are merely black boxes.
Towards Accurate Generative Models of Video: A New Metric & Challenges
To this extent we propose Fr\'{e}chet Video Distance (FVD), a new metric for generative models of video, and StarCraft 2 Videos (SCV), a benchmark of game play from custom starcraft 2 scenarios that challenge the current capabilities of generative models of video.
RUDDER: Return Decomposition for Delayed Rewards
In MDPs the Q-values are equal to the expected immediate reward plus the expected future rewards.
Ranked #9 on
Atari Games
on Atari 2600 Bowling
Fréchet ChemNet Distance: A metric for generative models for molecules in drug discovery
We propose a novel distance measure between two sets of molecules, called Fr\'echet ChemNet distance (FCD), that can be used as an evaluation metric for generative models.
First Order Generative Adversarial Networks
To formally describe an optimal update direction, we introduce a theoretical framework which allows the derivation of requirements on both the divergence and corresponding method for determining an update direction, with these requirements guaranteeing unbiased mini-batch updates in the direction of steepest descent.
Ranked #3 on
Image Generation
on LSUN Bedroom 64 x 64
Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields
We prove that Coulomb GANs possess only one Nash equilibrium which is optimal in the sense that the model distribution equals the target distribution.
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible.
Ranked #2 on
Image Generation
on LSUN Bedroom 64 x 64
Self-Normalizing Neural Networks
We introduce self-normalizing neural networks (SNNs) to enable high-level abstract representations.
Ranked #8 on
Drug Discovery
on Tox21
Speeding up Semantic Segmentation for Autonomous Driving
We propose a novel deep network architecture for image segmentation that keeps the high accuracy while being efficient enough for embedded devices.
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
In contrast to ReLUs, ELUs have negative values which allows them to push mean unit activations closer to zero like batch normalization but with lower computational complexity.
Ranked #145 on
Image Classification
on CIFAR-100
(using extra training data)
Toxicity Prediction using Deep Learning
The goal of this challenge was to assess the performance of computational methods in predicting the toxicity of chemical compounds.
