# Hybrid Knowledge Routed Modules for Large-scale Object Detection

arXiv: https://arxiv.org/abs/1810.12681 · HTML: https://mlsanity.com/paper/1810.12681/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2018.

## Built on by (most cited first, 14 of 14)

- [DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection](https://mlsanity.com/paper/2209.09407/) (2022)
- [Relation DETR: Exploring Explicit Position Relation Prior for Object Detection](https://mlsanity.com/paper/2407.11699/) (2024)
- [Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection](https://mlsanity.com/paper/2105.10160/) (2021)
- [Improving Scene Graph Classification by Exploiting Knowledge from Texts](https://mlsanity.com/paper/2102.04760/) (2021)
- [A Survey on Visual Transfer Learning using Knowledge Graphs](https://mlsanity.com/paper/2201.11794/) (2022)
- [NASOA: Towards Faster Task-oriented Online Fine-tuning with a Zoo of Models](https://mlsanity.com/paper/2108.03434/) (2021)
- [CSPENet: Contour-Aware and Saliency Priors Embedding Network for Infrared Small Target Detection](https://mlsanity.com/paper/2505.09943/) (2025)
- [RelMap: Enhancing Online Map Construction with Class-Aware Spatial Relation and Semantic Priors](https://mlsanity.com/paper/2507.21567/) (2025)
- [Relational Prior Knowledge Graphs for Detection and Instance Segmentation](https://mlsanity.com/paper/2310.07573/) (2023)
- [HR-RCNN: Hierarchical Relational Reasoning for Object Detection](https://mlsanity.com/paper/2110.13892/) (2021)
- [Knowledge-Integrated Informed AI for National Security](https://mlsanity.com/paper/2202.03188/) (2022)
- [Detecting Objects with Context-Likelihood Graphs and Graph Refinement](https://mlsanity.com/paper/2212.12395/) (2022)
- [Informed Machine Learning, Centrality, CNN, Relevant Document Detection, Repatriation of Indigenous Human Remains](https://mlsanity.com/paper/2303.14475/) (2023)
- [Meta Learning not to Learn: Robustly Informing Meta-Learning under Nuisance-Varying Families](https://mlsanity.com/paper/2503.04570/) (2025)

## Abstract (arXiv)

The dominant object detection approaches treat the recognition of each region separately and overlook crucial semantic correlations between objects in one scene. This paradigm leads to substantial performance drop when facing heavy long-tail problems, where very few samples are available for rare classes and plenty of confusing categories exists. We exploit diverse human commonsense knowledge for reasoning over large-scale object categories and reaching semantic coherency within one image. Particularly, we present Hybrid Knowledge Routed Modules (HKRM) that incorporates the reasoning routed by two kinds of knowledge forms: an explicit knowledge module for structured constraints that are summarized with linguistic knowledge (e.g. shared attributes, relationships) about concepts; and an implicit knowledge module that depicts some implicit constraints (e.g. common spatial layouts). By functioning over a region-to-region graph, both modules can be individualized and adapted to coordinate with visual patterns in each image, guided by specific knowledge forms. HKRM are light-weight, general-purpose and extensible by easily incorporating multiple knowledge to endow any detection networks the ability of global semantic reasoning. Experiments on large-scale object detection benchmarks show HKRM obtains around 34.5% improvement on VisualGenome (1000 categories) and 30.4% on ADE in terms of mAP. Codes and trained model can be found in https://github.com/chanyn/HKRM.