SMArT: Training Shallow Memory-aware Transformers for Robotic Explainability

By Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara. 2019

29 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Safety, Robustness & Interpretability, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Safety, Robustness & Interpretability

In Robotics & Control

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “Transformers can also help explain image captions visually [315] .”
From Show to Tell: A Survey on Deep Learning-Based Image Captioning (2021, background): “Finally, the Coverage score [84], [164] expresses the completeness of a caption, which is evaluated by considering the mentioned scene visual entities.”
Universal Captioner: Long-Tail Vision-and-Language Model Training through Content-Style Separation (2021, methodology): “Further, we employ a coverage-based metric inspired from [7, 8] between ground-truth detections or class annotations and the predicted caption.”
From Show to Tell: A Survey on Image Captioning (2021, methodology): “[69], [71] proposed a Transformer-based architecture where the selfattention operator of each encoder layer is augmented with a set of memory vectors.”