It Isn't Sh!tposting, It's My CAT Posting

TL;DR

This paper introduces CATNet, a novel architecture that generates humorous image captions by combining image captioning with a hilarious text conversion, making it easy for users to create funny content effortlessly.

Contribution

The paper presents a new two-stage architecture that first generates normal captions and then converts them into humorous captions, a novel approach in image captioning.

Findings

Successfully generates humorous captions from images.

Can produce funny text from normal captions using the transformer.

Flexible architecture allowing standalone hilarious caption generation.

Abstract

In this paper, we describe a novel architecture which can generate hilarious captions for a given input image. The architecture is split into two halves, i.e. image captioning and hilarious text conversion. The architecture starts with a pre-trained CNN model, VGG16 in this implementation, and applies attention LSTM on it to generate normal caption. These normal captions then are fed forward to our hilarious text conversion transformer which converts this text into something hilarious while maintaining the context of the input image. The architecture can also be split into two halves and only the seq2seq transformer can be used to generate hilarious caption by inputting a sentence.This paper aims to help everyday user to be more lazy and hilarious at the same time by generating captions using CATNet.