Search Results for author:
Found 23 papers, 10 papers with code
eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers
Therefore, in contrast to existing works, we propose to train an ensemble of text-to-image diffusion models specialized for different synthesis stages.
Ranked #9 on
Text-to-Image Generation
on COCO
A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes
While datasets with single-label supervision have propelled rapid advances in image classification, additional annotations are necessary in order to quantitatively assess how models make predictions.
Multi-Domain Self-Supervised Learning
In fact, training these methods on a combination of several domains often degrades the quality of learned representations compared to the models trained on a single domain.
Understanding Overparameterization in Generative Adversarial Networks
We also empirically study the role of model overparameterization in GANs using several large-scale experiments on CIFAR-10 and Celeb-A datasets.
Analyzing Attention Mechanisms through Lens of Sample Complexity and Loss Landscape
Attention mechanisms have advanced state-of-the-art deep learning models in many machine learning tasks.
Understanding Over-parameterization in Generative Adversarial Networks
In this work, we present a comprehensive analysis of the importance of model over-parameterization in GANs both theoretically and empirically.
Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation
To remedy this issue, robust formulations of OT with unbalanced marginal constraints have previously been proposed.
The Effectiveness of Memory Replay in Large Scale Continual Learning
However, a degraded performance is observed for ER with small memory.
Winning Lottery Tickets in Deep Generative Models
In this paper, we confirm the existence of winning tickets in deep generative models such as GANs and VAEs.
Learning to Balance Specificity and Invariance for In and Out of Domain Generalization
For domain generalization, the goal is to learn from a set of source domains to produce a single model that will best generalize to an unseen target domain.
Ranked #17 on
Domain Generalization
on DomainNet
Curriculum Manager for Source Selection in Multi-Source Domain Adaptation
In this paper, we proposed an adversarial agent that learns a dynamic curriculum for source samples, called Curriculum Manager for Source Selection (CMSS).
Multi-Source Unsupervised Domain Adaptation
Unsupervised Domain Adaptation
Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders
Detecting out of distribution (OOD) samples is of paramount importance in all Machine Learning applications.
Out of Distribution (OOD) Detection
Representation Learning
+1
Invert and Defend: Model-based Approximate Inversion of Generative Adversarial Networks for Secure Inference
Additionally, we show how InvGAN can be used to implement reparameterization white-box attacks on projection-based defense mechanisms.
Adversarial Robustness of Flow-Based Generative Models
Finally, using a hybrid adversarial training procedure, we significantly boost the robustness of these generative models.
Instance adaptive adversarial training: Improved accuracy tradeoffs in neural nets
Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks.
Normalized Wasserstein for Mixture Distributions With Applications in Adversarial Learning and Domain Adaptation
Using the proposed normalized Wasserstein measure leads to significant performance gains for mixture distributions with imbalanced mixture proportions compared to the vanilla Wasserstein distance.
Understanding Attention Mechanisms
Attention mechanisms have advanced the state of the art in several machine learning tasks.
Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation
Using the proposed normalized Wasserstein measure leads to significant performance gains for mixture distributions with imbalanced mixture proportions compared to the vanilla Wasserstein distance.
MetaReg: Towards Domain Generalization using Meta-Regularization
Training models that generalize to new domains at test time is a problem of fundamental importance in machine learning.
Ranked #44 on
Domain Generalization
on PACS
Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs
Building on the success of deep learning, two modern approaches to learn a probability model from the data are Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs).
Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation
In this work, we focus on adapting the representations learned by segmentation networks across synthetic and real domains.
Unrolling the Shutter: CNN to Correct Motion Distortions
Our single-image correction method fares well even operating in a frame-by-frame manner against video-based methods and performs better than scene-specific correction schemes even under challenging situations.
Generate To Adapt: Aligning Domains using Generative Adversarial Networks
Domain Adaptation is an actively researched problem in Computer Vision.
Ranked #20 on
Domain Adaptation
on Office-31
