AI Chat AI Image Generator AI Video Text to Speech

Fully Convolutional Networks for Text Classification

02/14/2019

∙

by Jacob Anderson, et al.

∙

∙

In this work I propose a new way of using fully convolutional networks for classification while allowing for input of any size. I additionally propose two modifications on the idea of attention and the benefits and detriments of using the modifications. Finally, I show suboptimal results on the ITAmoji 2018 tweet to emoji task and provide a discussion about why that might be the case as well as a proposed fix to further improve results.

research

∙ 03/20/2022

Fully Convolutional Fractional Scaling

We introduce a fully convolutional fractional scaling component, FCFS. F...

0 Michael Soloveitchik, et al. ∙

research

∙ 07/25/2023

Object-based Probabilistic Similarity Evidence of Sparse Latent Features from Fully Convolutional Networks

Similarity analysis using neural networks has emerged as a powerful tech...

0 Cyril Juliani, et al. ∙

research

∙ 11/25/2022

On the Universal Approximation Property of Deep Fully Convolutional Neural Networks

We study the approximation of shift-invariant or equivariant functions b...

0 Ting Lin, et al. ∙

research

∙ 10/07/2018

Image Completion on CIFAR-10

This project performed image completion on CIFAR-10, a dataset of 60,000...

0 Mason Swofford, et al. ∙

research

∙ 04/25/2021

Accuracy Improvement for Fully Convolutional Networks via Selective Augmentation with Applications to Electrocardiogram Data

Deep learning methods have shown suitability for time series classificat...

0 Lucas Cassiel Jacaruso, et al. ∙

research

∙ 01/20/2017

Fusion of Heterogeneous Data in Convolutional Networks for Urban Semantic Labeling (Invited Paper)

In this work, we present a novel module to perform fusion of heterogeneo...

0 Nicolas Audebert, et al. ∙

research

∙ 03/05/2017

Perceiving and Reasoning About Liquids Using Fully Convolutional Networks

Liquids are an important part of many common manipulation tasks in human...

0 Conor Schenck, et al. ∙