TMLR certificationsJun 27, 2023

New #FeaturedCertification:

Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration

Mauricio Delbracio, Peyman Milanfar

https://openreview.net/forum?id=VmyFF5lL3F

#denoising #restoration #deblurring

Inversion by Direct Iteration: An Alternative to Denoising...

Inversion by Direct Iteration (InDI) is a new formulation for supervised image restoration that avoids the so-called ``regression to the mean'' effect and produces more realistic and detailed...

OpenReview
TMLR certificationsJun 15, 2023

New #FeaturedCertification:

LEAD: Min-Max Optimization from a Physical Perspective

Reyhane Askari Hemmat, Amartya Mitra, Guillaume Lajoie, Ioannis Mitliagkas

https://openreview.net/forum?id=vXSsTYs6ZB

#gans #gan #adversarial

LEAD: Min-Max Optimization from a Physical Perspective

Adversarial formulations such as generative adversarial networks (GANs) have rekindled interest in two-player min-max games. A central obstacle in the optimization of such games is the rotational...

OpenReview
TMLR certificationsMay 22, 2023

New #FeaturedCertification:

Generalizability of Adversarial Robustness Under Distribution Shifts

Kumail Alhamoud, Hasan Abed Al Kader Hammoud, Motasem Alfarra, Bernard Ghanem

https://openreview.net/forum?id=XNFo3dQiCJ

#adversarial #robustness #robust

Generalizability of Adversarial Robustness Under Distribution Shifts

Recent progress in empirical and certified robustness promises to deliver reliable and deployable Deep Neural Networks (DNNs). Despite that success, most existing evaluations of DNN robustness have...

OpenReview
TMLR certificationsMay 16, 2023

New #FeaturedCertification:

Attacking Perceptual Similarity Metrics

Abhijay Ghildyal, Feng Liu

https://openreview.net/forum?id=r9vGSpbbRO

#adversarial #attacks #robustness

Attacking Perceptual Similarity Metrics

Perceptual similarity metrics have progressively become more correlated with human judgments on perceptual similarity; however, despite recent advances, the addition of an imperceptible distortion...

OpenReview
TMLR certificationsMar 21, 2023

New #FeaturedCertification:

Identification of Negative Transfers in Multitask Learning Using Surrogate Models

Dongyue Li, Huy Nguyen, Hongyang Ryan Zhang

https://openreview.net/forum?id=KgfFAI9f3E

#multitask #tasks #surrogate

Identification of Negative Transfers in Multitask Learning Using...

Multitask learning is widely used in practice to train a low-resource target task by augmenting it with multiple related source tasks. Yet, naively combining all the source tasks with a target task...

OpenReview
TMLR certificationsMar 16, 2023

New #FeaturedCertification:

Patches Are All You Need?

Asher Trockman, J Zico Kolter

https://openreview.net/forum?id=rAnB7JSMXL

#attention #convolutional #vision

Patches Are All You Need?

Although convolutional neural networks have been the dominant architecture for computer vision for many years, Vision Transformers (ViTs) have recently shown promise as an alternative. Subsequently...

OpenReview
TMLR certificationsMar 7, 2023

New #FeaturedCertification:

Numerical Accounting in the Shuffle Model of Differential Privacy

Antti Koskela, Mikko A. Heikkilä, Antti Honkela

https://openreview.net/forum?id=11osftjEbF

#shufflers #randomisation #shuffle

Numerical Accounting in the Shuffle Model of Differential Privacy

Shuffle model of differential privacy is a novel distributed privacy model based on a combination of local privacy mechanisms and a secure shuffler. It has been shown that the additional...

OpenReview
TMLR certificationsFeb 21, 2023

New #FeaturedCertification:

Workflow Discovery from Dialogues in the Low Data Regime

Amine El hattami, Issam H. Laradji, Stefania Raimondo, David Vazquez, Pau Rodriguez, Christopher Pal

https://openreview.net/forum?id=L9othQvPks

#dialogues #workflows #dialogue

Workflow Discovery from Dialogues in the Low Data Regime

Text-based dialogues are now widely used to solve real-world problems. In cases where solution strategies are already known, they can sometimes be codified into workflows and used to guide humans...

OpenReview
TMLR certificationsFeb 13, 2023

New #FeaturedCertification:

SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch

Jinsung Yoon, Kihyuk Sohn, Chun-Liang Li, Sercan O Arik, Tomas Pfister

https://openreview.net/forum?id=JwDpZSv3yz

#classifiers #supervised #labeling

SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch

Semi-supervised anomaly detection is a common problem, as often the datasets containing anomalies are partially labeled. We propose a canonical framework: Semi-supervised Pseudo-labeler Anomaly...

OpenReview
TMLR certificationsFeb 4, 2023

New #FeaturedCertification:

SolidGen: An Autoregressive Model for Direct B-rep Synthesis

Pradeep Kumar Jayaraman, Joseph George Lambourne, Nishkrit Desai et al.

https://openreview.net/forum?id=ZR2CDgADRo

#modeling #cad #sketch

SolidGen: An Autoregressive Model for Direct B-rep Synthesis

The Boundary representation (B-rep) format is the de-facto shape representation in computer-aided design (CAD) to model solid and sheet objects. Recent approaches to generating CAD models have...

OpenReview