About

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Greatest papers with code

Group Equivariant Convolutional Networks

24 Feb 2016adambielski/pytorch-gconv-experiments

We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries.

BREAST TUMOUR CLASSIFICATION COLORECTAL GLAND SEGMENTATION: MULTI-TISSUE NUCLEUS SEGMENTATION ROTATED MNIST

Domain Generalization using Causal Matching

arXiv 2020 microsoft/robustdg

Based on a general causal model for data from multiple domains, we show that prior methods for learning an invariant representation optimize for an incorrect objective.

DATA AUGMENTATION DOMAIN GENERALIZATION ROTATED MNIST

DIVA: Domain Invariant Variational Autoencoders

24 May 2019AMLab-Amsterdam/DIVA

We consider the problem of domain generalization, namely, how to learn representations given data from a set of domains that generalize to data from a previously unseen domain.

DOMAIN GENERALIZATION ROTATED MNIST

CapsGAN: Using Dynamic Routing for Generative Adversarial Networks

7 Jun 2018raeidsaqur/CapsGAN

We show that CapsGAN performs better than or equal to traditional CNN based GANs in generating images with high geometric transformations using rotated MNIST.

IMAGE GENERATION ROTATED MNIST

Polar Transformer Networks

ICLR 2018 daniilidis-group/polar-transformer-networks

The result is a network invariant to translation and equivariant to both rotation and scale.

ROTATED MNIST

Deep Rotation Equivariant Network

24 May 2017microljy/DREN

Recently, learning equivariant representations has attracted considerable research attention.

ROTATED MNIST

CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution Layers

21 Jul 2020mcrl/CyCNN

Deep Convolutional Neural Networks (CNNs) are empirically known to be invariant to moderate translation but not to rotation in image classification.

CLASSIFICATION DATA AUGMENTATION IMAGE CLASSIFICATION ROTATED MNIST

VideoOneNet: Bidirectional Convolutional Recurrent OneNet with Trainable Data Steps for Video Processing

ICML 2020 srph25/videoonenet

Deep Neural Networks (DNNs) achieve the state-of-the-art results on a wide range of image processing tasks, however, the majority of such solutions are problem-specific, like most AI algorithms.

COLORIZATION COMPRESSIVE SENSING DEBLURRING DENOISING ROTATED MNIST SUPER-RESOLUTION