# Spatial Knowledge Distillation to aid Visual Reasoning

arXiv: https://arxiv.org/abs/1812.03631 · HTML: https://mlsanity.com/paper/1812.03631/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2018.

## Built on by (most cited first, 5 of 5)

- [Respecting Transfer Gap in Knowledge Distillation](https://mlsanity.com/paper/2210.12787/) (2022)
- [GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation](https://mlsanity.com/paper/2402.11401/) (2024)
- [Inferring spatial relations from textual descriptions of images](https://mlsanity.com/paper/2102.00997/) (2021)
- [DistilDoc: Knowledge Distillation for Visually-Rich Document Applications](https://mlsanity.com/paper/2406.08226/) (2024)
- [Augmented Vision-Language Models: A Systematic Review](https://mlsanity.com/paper/2507.22933/) (2025)

## Abstract (arXiv)

For tasks involving language and vision, the current state-of-the-art methods tend not to leverage any additional information that might be present to gather relevant (commonsense) knowledge. A representative task is Visual Question Answering where large diagnostic datasets have been proposed to test a system's capability of answering questions about images. The training data is often accompanied by annotations of individual object properties and spatial locations. In this work, we take a step towards integrating this additional privileged information in the form of spatial knowledge to aid in visual reasoning. We propose a framework that combines recent advances in knowledge distillation (teacher-student framework), relational reasoning and probabilistic logical languages to incorporate such knowledge in existing neural networks for the task of Visual Question Answering. Specifically, for a question posed against an image, we use a probabilistic logical language to encode the spatial knowledge and the spatial understanding about the question in the form of a mask that is directly provided to the teacher network. The student network learns from the ground-truth information as well as the teachers prediction via distillation. We also demonstrate the impact of predicting such a mask inside the teachers network using attention. Empirically, we show that both the methods improve the test accuracy over a state-of-the-art approach on a publicly available dataset.