Research in NLP has mainly focused on factoid questions, with the goal of finding quick and reliable ways of matching a query to an answer.
We propose a new approach for propagating stable probability distributions through neural networks.
We quantitatively show the value of exposing the beam search tree and present five detailed analysis scenarios addressing the identified challenges.
To the best of our knowledge we are the first to present a framework for 2D/3D animal posture and trajectory tracking that works in both indoor and outdoor environments for up to 10 individuals.
We apply ProSpect in various personalized attribute-aware image generation applications, such as image-guided or text-driven manipulations of materials, style, and layout, achieving previously unattainable results from a single image input without fine-tuning the diffusion models.
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.
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
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.
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.
Sorting and ranking supervision is a method for training neural networks end-to-end based on ordering constraints.
Given a set of star glyphs associated to multiple class labels, we propose to use shape context descriptors to measure the perceptual distance between pairs of glyphs, and use the derived silhouette coefficient to measure the perception of class separability within the entire set.
Artificial neural networks revolutionized many areas of computer science in recent years since they provide solutions to a number of previously unsolved problems.
We present a framework that allows users to incorporate the semantics of their domain knowledge for topic model refinement while remaining model-agnostic.
The long-coveted task of reconstructing 3D geometry from images is still a standing problem.