We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image
classification. It is a simple residual network that alternates (i) a linear layer in which image …

Much of the recent progress made in image classification research can be credited to
training procedure refinements, such as changes in data augmentations and optimization …

Can we leverage high-resolution information without the unsustainable quadratic complexity
to input scale? We propose Traversal Network (TNet), a novel multi-scale hard-attention …

We propose a simple yet effective method to reduce the redundancy of DenseNet by
substantially decreasing the number of stacked modules by replacing the original bottleneck …

Unsupervised learning and supervised learning are key research topics in deep learning.
However, as high-capacity supervised neural networks trained with a large amount of labels …

We propose an end-to-end-trainable attention module for convolutional neural network
(CNN) architectures built for image classification. The module takes as input the 2D feature …

The depth and width of the network have been investigated to influence the performance of
image classification during the resent research. Wide residual networks (WRNs) have …

Deep residual networks (ResNets) made a recent breakthrough in deep learning. The core
idea of ResNets is to have shortcut connections between layers that allow the network to be …

In this paper we investigate image classification with computational resource limits at test
time. Two such settings are: 1. anytime classification, where the network's prediction for a …

Supervised learning using deep convolutional neural network has shown its promise in
large-scale image classification task. As a building block, it is now well positioned to be part …