Search Results for author:
Found 11 papers, 2 papers with code
No Shifted Augmentations (NSA): compact distributions for robust self-supervised Anomaly Detection
We propose novel architectural modifications to the self-supervised feature learning step, that enable such compact distributions for ID data to be learned.
Out of Distribution (OOD) Detection
Self-Supervised Anomaly Detection
+2
No Shifted Augmentations (NSA): strong baselines for self-supervised Anomaly Detection
We propose novel architectural modifications to the self-supervised feature learning step, that enable such compact ID distributions to be learned.
Out of Distribution (OOD) Detection
Self-Supervised Anomaly Detection
+3
Universum GANs: Improving GANs through contradictions
Limited availability of labeled-data makes any supervised learning problem challenging.
Stabilizing Bi-Level Hyperparameter Optimization using Moreau-Yosida Regularization
This research proposes to use the Moreau-Yosida envelope to stabilize the convergence behavior of bi-level Hyperparameter optimization solvers, and introduces the new algorithm called Moreau-Yosida regularized Hyperparameter Optimization (MY-HPO) algorithm.
Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey
With the general trend of increasing Convolutional Neural Network (CNN) model sizes, model compression and acceleration techniques have become critical for the deployment of these models on edge devices.
Auptimizer -- an Extensible, Open-Source Framework for Hyperparameter Tuning
Tuning machine learning models at scale, especially finding the right hyperparameter values, can be difficult and time-consuming.
On-Device Machine Learning: An Algorithms and Learning Theory Perspective
However, on-device learning is an expansive field with connections to a large number of related topics in AI and machine learning (including online learning, model adaptation, one/few-shot learning, etc.).
Improving Model Training by Periodic Sampling over Weight Distributions
In this paper, we explore techniques centered around periodic sampling of model weights that provide convergence improvements on gradient update methods (vanilla \acs{SGD}, Momentum, Adam) for a variety of vision problems (classification, detection, segmentation).
Is it Safe to Drive? An Overview of Factors, Challenges, and Datasets for Driveability Assessment in Autonomous Driving
Furthermore, by discussions of what driving scenarios are not covered by existing public datasets and what driveability factors need more investigation and data acquisition, this paper aims to encourage both targeted dataset collection and the proposal of novel driveability metrics that enhance the robustness of autonomous cars in adverse environments.
Make (Nearly) Every Neural Network Better: Generating Neural Network Ensembles by Weight Parameter Resampling
We perform a variety of analysis using the MNIST dataset and validate the approach with a number of DNN models using pre-trained models on the ImageNet dataset.
Effective Building Block Design for Deep Convolutional Neural Networks using Search
We apply this technique to generate models for multiple image datasets and show that these models achieve performance comparable to state-of-the-art (and even surpassing the state-of-the-art in one case).
