Search Results for author:
Found 14 papers, 9 papers with code
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
The new models reduce to PFGM when $D{=}1$ and to diffusion models when $D{\to}\infty$.
Ranked #1 on
Image Generation
on FFHQ 64x64 - 4x upscaling
Stable Target Field for Reduced Variance Score Estimation in Diffusion Models
We show that the procedure indeed helps in the challenging intermediate regime by reducing (the trace of) the covariance of training targets.
Ranked #5 on
Image Generation
on CIFAR-10
Poisson Flow Generative Models
We interpret the data points as electrical charges on the $z=0$ hyperplane in a space augmented with an additional dimension $z$, generating a high-dimensional electric field (the gradient of the solution to Poisson equation).
Ranked #20 on
Image Generation
on CIFAR-10
Controlling Directions Orthogonal to a Classifier
We propose to identify directions invariant to a given classifier so that these directions can be controlled in tasks such as style transfer.
Deep Joint Demosaicing and High Dynamic Range Imaging within a Single Shot
For the former challenge, a spatially varying convolution (SVC) is designed to process the Bayer images carried with varying exposures.
Novel Intensity Mapping Functions: Weighted Histogram Averaging
It is challenging to align the brightness distribution of the images with different exposures due to possible color distortion and loss of details in the brightest and darkest regions of input images.
Learning Representations that Support Robust Transfer of Predictors
We further demonstrate the impact of optimizing such transfer risk on two controlled settings, each representing a different pattern of environment shift, as well as on two real-world datasets.
Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?
Can models with particular structure avoid being biased towards spurious correlation in out-of-distribution (OOD) generalization?
Anytime Sampling for Autoregressive Models via Ordered Autoencoding
Experimentally, we demonstrate in several image and audio generation tasks that sample quality degrades gracefully as we reduce the computational budget for sampling.
TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
In this paper, we propose a novel information-theoretic approach, namely \textbf{T}otal \textbf{C}orrelation \textbf{G}ain \textbf{M}aximization (TCGM), for semi-supervised multi-modal learning, which is endowed with promising properties: (i) it can utilize effectively the information across different modalities of unlabeled data points to facilitate training classifiers of each modality (ii) it has theoretical guarantee to identify Bayesian classifiers, i. e., the ground truth posteriors of all modalities.
A Theory of Usable Information Under Computational Constraints
We propose a new framework for reasoning about information in complex systems.
L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise
To the best of our knowledge, L_DMI is the first loss function that is provably robust to instance-independent label noise, regardless of noise pattern, and it can be applied to any existing classification neural networks straightforwardly without any auxiliary information.
Ranked #33 on
Image Classification
on Clothing1M
(using extra training data)
L_DMI: An Information-theoretic Noise-robust Loss Function
\emph{To the best of our knowledge, $\mathcal{L}_{DMI}$ is the first loss function that is provably robust to instance-independent label noise, regardless of noise pattern, and it can be applied to any existing classification neural networks straightforwardly without any auxiliary information}.
Ranked #33 on
Image Classification
on Clothing1M
Max-MIG: an Information Theoretic Approach for Joint Learning from Crowds
Furthermore, we devise an accurate data-crowds forecaster that employs both the data and the crowdsourced labels to forecast the ground truth.
