Search Results for author:
Found 21 papers, 10 papers with code
Uncertainty Quantification via Stable Distribution Propagation
We propose a new approach for propagating stable probability distributions through neural networks.
Grounding Everything: Emerging Localization Properties in Vision-Language Transformers
To leverage those capabilities, we propose a Grounding Everything Module (GEM) that generalizes the idea of value-value attention introduced by CLIPSurgery to a self-self attention path.
Neural Machine Translation for Mathematical Formulae
We tackle the problem of neural machine translation of mathematical formulae between ambiguous presentation languages and unambiguous content languages.
ISAAC Newton: Input-based Approximate Curvature for Newton's Method
We present ISAAC (Input-baSed ApproximAte Curvature), a novel method that conditions the gradient using selected second-order information and has an asymptotically vanishing computational overhead, assuming a batch size smaller than the number of neurons.
Learning by Sorting: Self-supervised Learning with Group Ordering Constraints
Contrastive learning has become an important tool in learning representations from unlabeled data mainly relying on the idea of minimizing distance between positive data pairs, e. g., views from the same images, and maximizing distance between negative data pairs, e. g., views from different images.
Deep Differentiable Logic Gate Networks
Recently, research has increasingly focused on developing efficient neural network architectures.
Learning with Differentiable Algorithms
While classic computer science algorithms are suitable for precise execution of exactly defined tasks such as finding the shortest path in a large graph, neural networks allow learning from data to predict the most likely answer in more complex tasks such as image classification, which cannot be reduced to an exact algorithm.
Differentiable Top-k Classification Learning
In this work, we relax this assumption and optimize the model for multiple k simultaneously instead of using a single k. Leveraging recent advances in differentiable sorting and ranking, we propose a differentiable top-k cross-entropy classification loss.
Ranked #58 on
Image Classification
on ImageNet
Domain Adaptation meets Individual Fairness. And they get along
In this paper, we leverage this connection between algorithmic fairness and distribution shifts to show that algorithmic fairness interventions can help ML models overcome distribution shifts, and that domain adaptation methods (for overcoming distribution shifts) can mitigate algorithmic biases.
GenDR: A Generalized Differentiable Renderer
In this work, we present and study a generalized family of differentiable renderers.
Monotonic Differentiable Sorting Networks
We introduce a family of sigmoid functions and prove that they produce differentiable sorting networks that are monotonic.
Post-processing for Individual Fairness
In this work, we propose general post-processing algorithms for individual fairness (IF).
Style Agnostic 3D Reconstruction via Adversarial Style Transfer
Recently introduced differentiable renderers can be leveraged to learn the 3D geometry of objects from 2D images, but those approaches require additional supervision to enable the renderer to produce an output that can be compared to the input image.
Learning with Algorithmic Supervision via Continuous Relaxations
The integration of algorithmic components into neural architectures has gained increased attention recently, as it allows training neural networks with new forms of supervision such as ordering constraints or silhouettes instead of using ground truth labels.
Propagating Distributions through Neural Networks
We propose a new approach to propagating probability distributions through neural networks.
A Sampling-Free Approximation of Gaussian Variational Auto-Encoders
We propose a sampling-free approximate formulation of Gaussian variational auto-encoders.
Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision
Sorting and ranking supervision is a method for training neural networks end-to-end based on ordering constraints.
$C^\infty$ Smooth Algorithmic Neural Networks for Solving Inverse Problems
Artificial neural networks revolutionized many areas of computer science in recent years since they provide solutions to a number of previously unsolved problems.
AlgoNet: $C^\infty$ Smooth Algorithmic Neural Networks
These networks integrate smooth versions of classic algorithms into the topology of neural networks.
Pix2Vex: Image-to-Geometry Reconstruction using a Smooth Differentiable Renderer
The long-coveted task of reconstructing 3D geometry from images is still a standing problem.
Towards Formula Translation using Recursive Neural Networks
We implemented the first translator for mathematical formulae based on recursive neural networks.
