SMArT: Training Shallow Memory-aware Transformers for Robotic Explainability

TL;DR

This paper introduces SMArT, a lightweight Transformer-based model with memory-aware encoding for robotic visual captioning, achieving high-quality explanations with reduced computational costs suitable for autonomous agents.

Contribution

The paper presents a novel shallow Transformer architecture with memory-aware encoding, balancing caption quality and computational efficiency for robotic explainability.

Findings

Achieves competitive caption quality with fewer Transformer layers.

Reduces computational demands compared to traditional models.

Demonstrates effectiveness in robotic perception scenarios.

Abstract

The ability to generate natural language explanations conditioned on the visual perception is a crucial step towards autonomous agents which can explain themselves and communicate with humans. While the research efforts in image and video captioning are giving promising results, this is often done at the expense of the computational requirements of the approaches, limiting their applicability to real contexts. In this paper, we propose a fully-attentive captioning algorithm which can provide state-of-the-art performances on language generation while restricting its computational demands. Our model is inspired by the Transformer model and employs only two Transformer layers in the encoding and decoding stages. Further, it incorporates a novel memory-aware encoding of image regions. Experiments demonstrate that our approach achieves competitive results in terms of caption quality while featuring reduced computational demands. Further, to evaluate its applicability on autonomous agents, we conduct experiments on simulated scenes taken from the perspective of domestic robots.