# SMArT: Training Shallow Memory-aware Transformers for Robotic Explainability

arXiv: https://arxiv.org/abs/1910.02974 · HTML: https://mlsanity.com/paper/1910.02974/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2019.

## Built on by (most cited first, 10 of 10)

- [From Show to Tell: A Survey on Deep Learning-based Image Captioning](https://mlsanity.com/paper/2107.06912/) (2021)
- [Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation](https://mlsanity.com/paper/2303.12112/) (2023)
- [Retrieval-Augmented Transformer for Image Captioning](https://mlsanity.com/paper/2207.13162/) (2022)
- [Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images](https://mlsanity.com/paper/2304.00500/) (2023)
- [CaMEL: Mean Teacher Learning for Image Captioning](https://mlsanity.com/paper/2202.10492/) (2022)
- [BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stronger Visual Cues](https://mlsanity.com/paper/2407.20341/) (2024)
- [Continual Transformers: Redundancy-Free Attention for Online Inference](https://mlsanity.com/paper/2201.06268/) (2022)
- [Embodied Agents for Efficient Exploration and Smart Scene Description](https://mlsanity.com/paper/2301.07150/) (2023)
- [Learning to Select: A Fully Attentive Approach for Novel Object Captioning](https://mlsanity.com/paper/2106.01424/) (2021)
- [Embodied Navigation at the Art Gallery](https://mlsanity.com/paper/2204.09069/) (2022)

## Abstract (arXiv)

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.