Year: 2017
Type: conference-paper
Abstract: We consider generation and comprehension of natural language referring expression for objects in an image. Unlike generic image captioning which lacks natural standard evaluation criteria, quality of a referring expression may be measured by the receivers ability to correctly infer which object is being described. Following this intuition, we propose two approaches to utilize models trained for comprehension task to generate better expressions. First, we use a comprehension module trained on human-generated expressions, as a critic of referring expression generator. The comprehension module serves as a differentiable proxy of human evaluation, providing training signal to the generation module. Second, we use the comprehension model in a generate-and-rerank pipeline, which chooses from candidate expressions generated by a model according to their performance on the comprehension task. We show that both approaches lead to improved referring expression generation on multiple benchmark datasets.
Authors: Ruotian Luo, Gregory Shakhnarovich
Institution: Toyota Technological Institute at Chicago
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Nvidia
OpenAlex ID: W2583360688
