Hybrid Knowledge Routed Modules for Large-scale Object Detection

Abstract

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.

9 pages, 5 figures

Cited by in corpus (14)

• Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
• Physical-Virtual Collaboration Modeling for Intra-and Inter-Station Metro Ridership Prediction
• Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning
• Learning Visual Commonsense for Robust Scene Graph Generation
• Bidirectional Graph Reasoning Network for Panoptic Segmentation
• Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings
• PK-GCN: Prior Knowledge Assisted Image Classification using Graph Convolution Networks
• Knowledge Enhanced Neural Fashion Trend Forecasting
• Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection
• A Quantitative Perspective on Values of Domain Knowledge for Machine Learning
• HR-RCNN: Hierarchical Relational Reasoning for Object Detection
• AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling
• Region Refinement Network for Salient Object Detection
• Saliency Prediction with External Knowledge