Search Results for author:
Found 21 papers, 5 papers with code
Layer Collaboration in the Forward-Forward Algorithm
We show that the current version of the forward-forward algorithm is suboptimal when considering information flow in the network, resulting in a lack of collaboration between layers of the network.
AutoFocusFormer: Image Segmentation off the Grid
To achieve this, we propose AutoFocusFormer (AFF), a local-attention transformer image recognition backbone, which performs adaptive downsampling by learning to retain the most important pixels for the task.
Ranked #4 on
Instance Segmentation
on Cityscapes val
Diffusion Probabilistic Fields
Diffusion probabilistic models have quickly become a major approach for generative modeling of images, 3D geometry, video and other domains.
DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data
In contrast, we propose a Discriminator gradIent Gap regularized GAN (DigGAN) formulation which can be added to any existing GAN.
Precondition Layer and Its Use for GANs
We use this PC-layer in two ways: 1) fixed preconditioning (FPC) adds a fixed PC-layer to all layers, and 2) adaptive preconditioning (APC) adaptively controls the strength of preconditioning.
Coordinated Multi-Agent Exploration Using Shared Goals
Exploration is critical for good results of deep reinforcement learning algorithms and has drawn much attention.
Towards a Better Global Loss Landscape of GANs
We also perform experiments to support our theory that RpGAN has a better landscape than separable-GAN.
NCP-VAE: Variational Autoencoders with Noise Contrastive Priors
To tackle this issue, we propose an energy-based prior defined by the product of a base prior distribution and a reweighting factor, designed to bring the base closer to the aggregate posterior.
Spatially Aware Multimodal Transformers for TextVQA
Further, each head in our multi-head self-attention layer focuses on a different subset of relations.
On the generalization of bayesian deep nets for multi-class classification
Generalization bounds which assess the difference between the true risk and the empirical risk have been studied extensively.
Enabling real-time multi-messenger astrophysics discoveries with deep learning
Multi-messenger astrophysics is a fast-growing, interdisciplinary field that combines data, which vary in volume and speed of data processing, from many different instruments that probe the Universe using different cosmic messengers: electromagnetic waves, cosmic rays, gravitational waves and neutrinos.
CP-GAN: Towards a Better Global Landscape of GANs
In this work, we perform a global analysis of GANs from two perspectives: the global landscape of the outer-optimization problem and the global behavior of the gradient descent dynamics.
PAC-Bayesian Neural Network Bounds
Bayesian neural networks, which both use the negative log-likelihood loss function and average their predictions using a learned posterior over the parameters, have been used successfully across many scientific fields, partly due to their ability to `effortlessly' extract desired representations from many large-scale datasets.
Deep Learning for Multi-Messenger Astrophysics: A Gateway for Discovery in the Big Data Era
We discuss key aspects to realize this endeavor, namely (i) the design and exploitation of scalable and computationally efficient AI algorithms for Multi-Messenger Astrophysics; (ii) cyberinfrastructure requirements to numerically simulate astrophysical sources, and to process and interpret Multi-Messenger Astrophysics data; (iii) management of gravitational wave detections and triggers to enable electromagnetic and astro-particle follow-ups; (iv) a vision to harness future developments of machine and deep learning and cyberinfrastructure resources to cope with the scale of discovery in the Big Data Era; (v) and the need to build a community that brings domain experts together with data scientists on equal footing to maximize and accelerate discovery in the nascent field of Multi-Messenger Astrophysics.
Learning Deep Parsimonious Representations
In this paper we aim at facilitating generalization for deep networks while supporting interpretability of the learned representations.
Constraints Based Convex Belief Propagation
Inference in Markov random fields subject to consistency structure is a fundamental problem that arises in many real-life applications.
Smooth and Strong: MAP Inference with Linear Convergence
Maximum a-posteriori (MAP) inference is an important task for many applications.
Efficient Inference of Continuous Markov Random Fields with Polynomial Potentials
In this paper, we prove that every multivariate polynomial with even degree can be decomposed into a sum of convex and concave polynomials.
Message Passing Inference for Large Scale Graphical Models with High Order Potentials
To keep up with the Big Data challenge, parallelized algorithms based on dual decomposition have been proposed to perform inference in Markov random fields.
Latent Structured Active Learning
In this paper we present active learning algorithms in the context of structured prediction problems.
Globally Convergent Dual MAP LP Relaxation Solvers using Fenchel-Young Margins
While finding the exact solution for the MAP inference problem is intractable for many real-world tasks, MAP LP relaxations have been shown to be very effective in practice.
