Learning to Generate Grounded Visual Captions without Localization Supervision

Chih-Yao Ma, Yannis Kalantidis, Ghassan AlRegib, Peter Vajda, Marcus Rohrbach, Zsolt Kira

Keywords: image captioning, video captioning, self-supervised learning, visual grounding

TL;DR: We improve visual grounding accuracy for both image and video captioning tasks without using ground-truth grounding annotations.

Abstract: When automatically generating a sentence description for an image or video, it often remains unclear how well the generated caption is grounded, or if the model hallucinates based on priors in the dataset and/or the language model. The most common way of relating image regions with words in caption models is through an attention mechanism over the regions that are used as input to predict the next word. The model must therefore learn to predict the attentional weights without knowing the word it should localize. This is difficult to train without grounding supervision since recurrent models can propagate past information and there is no explicit signal to force the captioning model to properly ground the individual decoded words. In this work, we help the model to achieve this via a novel cyclical training regimen that forces the model to localize each word in the image after the sentence decoder generates it, and then reconstruct the sentence from the localized image region(s) to match the ground-truth. Our proposed framework only requires learning one extra fully-connected layer (the localizer), a layer that can be removed at test time. We show that our model significantly improves grounding accuracy without relying on grounding supervision or introducing extra computation during inference for both image and video captioning tasks.

Code: https://www.dropbox.com/s/569iz5opptn3s8a/cyclical-grounding-code.zip?dl=1