Text-to-image generation (TTI) refers to the usage of models that could
...
Understanding the dynamics of large quantum systems is hindered by the c...
CNNs and Transformers have their own advantages and both have been widel...
How to enable learnability for new classes while keeping the capability ...
Neural image compression methods have seen increasingly strong performan...
Few-shot class-incremental learning (FSCIL) has been a challenging probl...
Convolution neural networks (CNNs) and Transformers have their own advan...
A recent study has shown a phenomenon called neural collapse in that the...
Panoptic Part Segmentation (PPS) unifies panoptic segmentation and part
...
Automated machine learning has been widely explored to reduce human effo...
Reference-based line-art colorization is a challenging task in computer
...
In this paper, we focus on exploring effective methods for faster, accur...
Motivated by biological evolution, this paper explains the rationality o...
Class imbalance distribution widely exists in real-world engineering.
Ho...
Modern deep neural networks for classification usually jointly learn a
b...
Point cloud classifiers with rotation robustness have been widely discus...
We present a simple and effective approach for posterior uncertainty
qua...
Neural compression is the application of neural networks and other machi...
Detection Transformer (DETR) and Deformable DETR have been proposed to
e...
Deformable image registration is able to achieve fast and accurate align...
Rate-distortion (R-D) function, a key quantity in information theory,
ch...
We develop biologically plausible training mechanisms for self-supervise...
While recent machine learning research has revealed connections between ...
We present a new type of acquisition functions for online decision makin...
Most differentiable neural architecture search methods construct a super...
Differentiable neural architecture search (DARTS) has gained much succes...
Recent work by Marino et al. (2020) showed improved performance in seque...
Neural architecture search (NAS) aims to produce the optimal sparse solu...
We consider the problem of lossy image compression with deep latent vari...
This paper presents a machine learning framework for Bayesian systems
id...
The convolution operation suffers from a limited receptive filed, while
...
The peridynamic theory reformulates the equations of continuum mechanics...
Deep Bayesian latent variable models have enabled new approaches to both...
A variety of lifted inference algorithms, which exploit model symmetry t...
The correspondence between residual networks and dynamical systems motiv...
The panoptic segmentation task requires a unified result from semantic a...
Self-attention mechanism has been widely used for various tasks. It is
d...
Advances in computational science offer a principled pipeline for predic...
We present a probabilistic deep learning methodology that enables the
co...
We consider the application of deep generative models in propagating
unc...
We present a deep learning framework for quantifying and propagating
unc...
Deep neural networks have been one of the dominant machine learning
appr...
Convolutional neural networks (CNNs) have recently achieved great succes...
We propose a simple and easy to implement neural network compression
alg...
Improving information flow in deep networks helps to ease the training
d...