Litcius/Paper detail

A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering

Alireza Salemi, Juan Altmayer Pizzorno, Hamed Zamani

202320 citationsDOI

Abstract

Knowledge-Intensive Visual Question Answering (KI-VQA) refers to answering a question about an image whose answer does not lie in the image. This paper presents a new pipeline for KI-VQA tasks, consisting of a retriever and a reader. First, we introduce DEDR, a symmetric dual encoding dense retrieval framework in which documents and queries are encoded into a shared embedding space using uni-modal (textual) and multi-modal encoders. We introduce an iterative knowledge distillation approach that bridges the gap between the representation spaces in these two encoders. Extensive evaluation on two well-established KI-VQA datasets, i.e., OK-VQA and FVQA, suggests that DEDR outperforms state-of-the-art baselines by 11.6% and 30.9% on OK-VQA and FVQA, respectively.

Topics & Concepts

Question answeringComputer scienceEmbeddingDual (grammatical number)Information retrievalEncoding (memory)Pipeline (software)EncoderImage (mathematics)Artificial intelligenceProgramming languageLiteratureOperating systemArtMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval TechniquesDomain Adaptation and Few-Shot Learning
A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering | Litcius