miscellaneous-1

Parameter Prediction

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in parameter-prediction-1

Trend

Dataset

Best Model

Actions

CIFAR10

Libraries

i

Use these libraries to find parameter-prediction-1 models and implementations

Datasets

DeepNets-1M

DrivAerNet

Subtasks

No subtasks available.

Most implemented papers

Diet Networks: Thin Parameters for Fat Genomic

Adriana Romero, Yoshua Bengio, P. Carrier, Tristan Sylvain, Akram Erraqabi, Alex Auvolat, Etienne Dejoie, Marc-André Legault, M. Dubé, J. Hussin•Thu Nov 03 2016

A novel neural network parametrization is proposed which considerably reduces the number of parameters and the error rate of the classifier on tasks in which the input is a description of the genetic variation specific to a patient, the single nucleotide polymorphisms, yielding millions of ternary inputs.

75

Content

0

Paper Graph

WISE: Whitebox Image Stylization by Example-based Learning

M. Reimann, Amir Semmo, J. Dollner, Matthias Trapp, Winfried Lotzsch, Martin Bussemeyer•Thu Jul 28 2022

WISE is presented, an example-based image-processing system that can handle a multitude of stylization techniques, such as watercolor, oil or cartoon stylization, within a common framework and it is demonstrated that jointly training an XDoG filter and a CNN for postprocessing can achieve comparable results to a state-of-the-art GAN-based method.

5 0

Paper Graph

Image Question Answering Using Convolutional Neural Network with Dynamic Parameter Prediction

Hyeonwoo Noh, Bohyung Han, P. H. Seo•Tue Nov 17 2015

The proposed network-joint network with the CNN for ImageQA and the parameter prediction network-is trained end-to-end through back-propagation, where its weights are initialized using a pre-trained CNN and GRU.

335 0

Paper Graph

Decision Trees for Decision-Making under the Predict-then-Optimize Framework

Adam N. Elmachtoub, Jason Cheuk Nam Liang, Ryan McNellis•Fri Feb 28 2020

It is demonstrated on these datasets that SPOTs simultaneously provide higher quality decisions and significantly lower model complexity than other machine learning approaches (e.g., CART) trained to minimize prediction error.

135 0

Paper Graph

Learning an Explicit Hyperparameter Prediction Policy Conditioned on Tasks

Deyu Meng, Zongben Xu, Jun Shu•Thu Dec 31 2020

This study interprets meta learning methodology as learning an explicit hyperparameter prediction policy shared by all training tasks, which guarantees that the meta-learned learning methodology is able to flexibly fit diverse query tasks, instead of only obtaining fixed hyperparameters by many current meta learning methods.

7 0

Paper Graph

Parameter Prediction for Unseen Deep Architectures

M. Drozdzal, Graham W. Taylor, Adriana Romero-Soriano, Boris Knyazev•Sun Oct 24 2021

This work proposes a hypernetwork that can predict performant parameters in a single forward pass taking a fraction of a second, even on a CPU, and learns a strong representation of neural architectures enabling their analysis.

99 0

Paper Graph

Estimating relative diffusion from 3D micro-CT images using CNNs

Stephan Gärttner, F. Frank, Fabian Woller, Andreas Meier, N. Ray•Wed Aug 03 2022

This paper demonstrates the ability of CNNs to perform predictions of relative diffusion directly from full pore-space geometries and conveniently fuses diffusion prediction and a well-established morphological model which describes phase distributions in partially saturated porous media.

6 0

Paper Graph

Forest Parameter Prediction by Multiobjective Deep Learning of Regression Models Trained with Pseudo-Target Imputation

Sara Björk, S. N. Anfinsen, Michael Kampffmeyer, E. Næsset, T. Gobakken, Lennart Noordermeer•Sun Jun 18 2023

This paper proposes to impute a sample of true prediction targets with data from an existing RS-based prediction map that is considered as pseudo-targets, and demonstrates that when a judicious combination of loss functions is used, the semi-supervised imputation strategy produces results that surpass traditional ALS-based regression models, even thoughsen data are considered as inferior for forest monitoring.

2 0

Paper Graph

Controlling Geometric Abstraction and Texture for Artistic Images

M. Reimann, Amir Semmo, J. Dollner, Matthias Trapp, Martin Bussemeyer, Benito Buchheim•Sun Jul 30 2023

The proposed decoupling of shape and texture enables various options for stylistic editing, including interactive global and local adjustments of shape, stroke, and painterly attributes such as surface relief and contours.

2 0

Paper Graph

Adding a benchmark result helps the community track progress.