Augmented Commonsense Knowledge for Remote Object Grounding

TL;DR

This paper introduces ACK, a novel model that leverages commonsense knowledge graphs from ConceptNet to improve visual and language understanding for remote object grounding in vision-and-language navigation tasks, achieving state-of-the-art results.

Contribution

The paper proposes an augmented commonsense knowledge model that integrates a refined knowledge graph into navigation agents, enhancing action prediction and data alignment in unseen environments.

Findings

Achieves state-of-the-art performance on REVERIE benchmark.

Effectively incorporates commonsense knowledge to improve navigation accuracy.

Outperforms baseline models significantly.

Abstract

The vision-and-language navigation (VLN) task necessitates an agent to perceive the surroundings, follow natural language instructions, and act in photo-realistic unseen environments. Most of the existing methods employ the entire image or object features to represent navigable viewpoints. However, these representations are insufficient for proper action prediction, especially for the REVERIE task, which uses concise high-level instructions, such as ''Bring me the blue cushion in the master bedroom''. To address enhancing representation, we propose an augmented commonsense knowledge model (ACK) to leverage commonsense information as a spatio-temporal knowledge graph for improving agent navigation. Specifically, the proposed approach involves constructing a knowledge base by retrieving commonsense information from ConceptNet, followed by a refinement module to remove noisy and irrelevant knowledge. We further present ACK which consists of knowledge graph-aware cross-modal and concept aggregation modules to enhance visual representation and visual-textual data alignment by integrating visible objects, commonsense knowledge, and concept history, which includes object and knowledge temporal information. Moreover, we add a new pipeline for the commonsense-based decision-making process which leads to more accurate local action prediction. Experimental results demonstrate our proposed model noticeably outperforms the baseline and archives the state-of-the-art on the REVERIE benchmark.