Revisiting Image-Language Networks for Open-ended Phrase Detection
This addresses a more realistic natural language grounding task for computer vision applications, though it is incremental as it extends Faster R-CNN.
The paper tackles the problem of open-ended phrase detection in images, where both relevance and localization must be determined, achieving over double the performance compared to naive methods on datasets with phrase vocabularies up to 159K.
Most existing work that grounds natural language phrases in images starts with the assumption that the phrase in question is relevant to the image. In this paper we address a more realistic version of the natural language grounding task where we must both identify whether the phrase is relevant to an image and localize the phrase. This can also be viewed as a generalization of object detection to an open-ended vocabulary, introducing elements of few- and zero-shot detection. We propose an approach for this task that extends Faster R-CNN to relate image regions and phrases. By carefully initializing the classification layers of our network using canonical correlation analysis (CCA), we encourage a solution that is more discerning when reasoning between similar phrases, resulting in over double the performance compared to a naive adaptation on three popular phrase grounding datasets, Flickr30K Entities, ReferIt Game, and Visual Genome, with test-time phrase vocabulary sizes of 5K, 32K, and 159K, respectively.