# Visual Concept Reasoning Networks

arXiv: https://arxiv.org/abs/2008.11783 · HTML: https://mlsanity.com/paper/2008.11783/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2020.

## Built on by (most cited first, 3 of 3)

- [Concept Bottleneck Model with Additional Unsupervised Concepts](https://mlsanity.com/paper/2202.01459/) (2022)
- [Sample-Efficient Learning of Novel Visual Concepts](https://mlsanity.com/paper/2306.09482/) (2023)
- [Knowledge-Guided Short-Context Action Anticipation in Human-Centric Videos](https://mlsanity.com/paper/2309.05943/) (2023)

## Abstract (arXiv)

A split-transform-merge strategy has been broadly used as an architectural constraint in convolutional neural networks for visual recognition tasks. It approximates sparsely connected networks by explicitly defining multiple branches to simultaneously learn representations with different visual concepts or properties. Dependencies or interactions between these representations are typically defined by dense and local operations, however, without any adaptiveness or high-level reasoning. In this work, we propose to exploit this strategy and combine it with our Visual Concept Reasoning Networks (VCRNet) to enable reasoning between high-level visual concepts. We associate each branch with a visual concept and derive a compact concept state by selecting a few local descriptors through an attention module. These concept states are then updated by graph-based interaction and used to adaptively modulate the local descriptors. We describe our proposed model by split-transform-attend-interact-modulate-merge stages, which are implemented by opting for a highly modularized architecture. Extensive experiments on visual recognition tasks such as image classification, semantic segmentation, object detection, scene recognition, and action recognition show that our proposed model, VCRNet, consistently improves the performance by increasing the number of parameters by less than 1%.