DenseCap: Fully Convolutional Localization Networks for Dense Captioning
This work addresses the problem of generating detailed, region-specific captions for images, which is a generalization of object detection and image captioning, for computer vision applications, though it is incremental as it builds on existing methods.
The paper tackles the dense captioning task, which requires localizing and describing salient image regions in natural language, by proposing a Fully Convolutional Localization Network (FCLN) that processes images efficiently in a single forward pass without external region proposals. It achieves speed and accuracy improvements over state-of-the-art baselines on the Visual Genome dataset with 94,000 images and 4.1 million captions.
We introduce the dense captioning task, which requires a computer vision system to both localize and describe salient regions in images in natural language. The dense captioning task generalizes object detection when the descriptions consist of a single word, and Image Captioning when one predicted region covers the full image. To address the localization and description task jointly we propose a Fully Convolutional Localization Network (FCLN) architecture that processes an image with a single, efficient forward pass, requires no external regions proposals, and can be trained end-to-end with a single round of optimization. The architecture is composed of a Convolutional Network, a novel dense localization layer, and Recurrent Neural Network language model that generates the label sequences. We evaluate our network on the Visual Genome dataset, which comprises 94,000 images and 4,100,000 region-grounded captions. We observe both speed and accuracy improvements over baselines based on current state of the art approaches in both generation and retrieval settings.