Improved Adversarial Image Captioning

Pierre Dognin, Igor Melnyk, Youssef Mroueh, Jarret Ross, Tom Sercu

Keywords: image captioning, discrete GAN training

TL;DR: Image captioning as a conditional GAN training with novel architectures, also study two discrete GAN training methods.

Abstract: In this paper we study image captioning as a conditional GAN training, proposing both a context-aware LSTM captioner and co-attentive discriminator, which enforces semantic alignment between images and captions. We investigate the viability of two discrete GAN training methods: Self-critical Sequence Training (SCST) and Gumbel Straight-Through (ST) and demonstrate that SCST shows more stable gradient behavior and improved results over Gumbel ST.