Context in object detection: a systematic literature review

2025-03-19

Artificial Intelligence Review

AI Summary

The role and modeling mechanisms of contextual information in object detection remain inadequately understood across diverse detection scenarios. Method: We conduct a systematic literature review (SLR) guided by the PRISMA framework, analyzing over 265 publications spanning seven domains: generic detection, video detection, small-object detection, camouflaged-object detection, few-shot detection, and others. Contribution/Results: We propose the first multi-dimensional taxonomy of context, categorizing modeling paradigms into scene-, semantic-, temporal-, and cross-modal contexts. Our analysis identifies zero-shot detection and context disentanglement as critical research gaps. Furthermore, we construct a comprehensive context-aware method map covering all major detection scenarios and introduce a reusable, integrated evaluation protocol. This work establishes a theoretical foundation and practical guideline for context-driven object detection models, enabling principled design and rigorous assessment of contextual reasoning in detection systems.

Technology Category

• Computer Vision: Object Detection & Categorization
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Context is an important factor in computer vision as it offers valuable information to clarify and analyze visual data. Utilizing the contextual information inherent in an image or a video can improve the precision and effectiveness of object detectors. For example, where recognizing an isolated object might be challenging, context information can improve comprehension of the scene. This study explores the impact of various context-based approaches to object detection. Initially, we investigate the role of context in object detection and survey it from several perspectives. We then review and discuss the most recent context-based object detection approaches and compare them. Finally, we conclude by addressing research questions and identifying gaps for further studies. More than 265 publications are included in this survey, covering different aspects of context in different categories of object detection, including general object detection, video object detection, small object detection, camouflaged object detection, zero-shot, one-shot, and few-shot object detection. This literature review presents a comprehensive overview of the latest advancements in context-based object detection, providing valuable contributions such as a thorough understanding of contextual information and effective methods for integrating various context types into object detection, thus benefiting researchers.

Problem

• Explores impact of context-based approaches on object detection
• Reviews recent context-based methods and compares their effectiveness
• Identifies research gaps in context-aware object detection techniques

Innovation

• Surveying context-based object detection approaches
• Comparing recent context integration methods
• Analyzing 265+ publications across detection categories