Uncertainty Aware Human-machine Collaboration in Camouflaged Object Detection

2025-02-12

AI Summary

This study addresses the challenge of trustworthy decision-making in camouflaged object detection (COD) by proposing the first human–AI collaboration framework integrating uncertainty quantification and brain–computer interface (BCI). Methodologically, we design a multi-view CNN backbone, develop a multi-view uncertainty estimation mechanism, and introduce an uncertainty-aware co-training strategy. We employ a rapid serial visual presentation (RSVP) BCI paradigm to validate low-confidence model predictions in real time and implement an uncertainty-driven dynamic task allocation scheme to optimize human–AI division of labor. Our key contributions are the first integration of uncertainty quantification and RSVP-BCI into COD. On the CAMO dataset, our method achieves average improvements of 4.56% in accuracy and 3.66% in F1-score; top-performing participants attain gains of 7.6% in balanced accuracy (BA) and 6.66% in F1-score. Empirical analysis confirms a strong positive correlation between prediction accuracy and confidence, and ablation studies validate the efficacy of each component.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Multi-modal Vision

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Camouflaged Object Detection (COD), the task of identifying objects concealed within their environments, has seen rapid growth due to its wide range of practical applications. A key step toward developing trustworthy COD systems is the estimation and effective utilization of uncertainty. In this work, we propose a human-machine collaboration framework for classifying the presence of camouflaged objects, leveraging the complementary strengths of computer vision (CV) models and noninvasive brain-computer interfaces (BCIs). Our approach introduces a multiview backbone to estimate uncertainty in CV model predictions, utilizes this uncertainty during training to improve efficiency, and defers low-confidence cases to human evaluation via RSVP-based BCIs during testing for more reliable decision-making. We evaluated the framework in the CAMO dataset, achieving state-of-the-art results with an average improvement of 4.56% in balanced accuracy (BA) and 3.66% in the F1 score compared to existing methods. For the best-performing participants, the improvements reached 7.6% in BA and 6.66% in the F1 score. Analysis of the training process revealed a strong correlation between our confidence measures and precision, while an ablation study confirmed the effectiveness of the proposed training policy and the human-machine collaboration strategy. In general, this work reduces human cognitive load, improves system reliability, and provides a strong foundation for advancements in real-world COD applications and human-computer interaction. Our code and data are available at: https://github.com/ziyuey/Uncertainty-aware-human-machine-collaboration-in-camouflaged-object-identification.

Problem

• Enhancing trust in Camouflaged Object Detection systems
• Leveraging human-machine collaboration for accurate detection
• Utilizing uncertainty estimation to improve decision-making reliability

Innovation

• Multiview backbone for uncertainty estimation
• RSVP-based BCIs for human evaluation
• Training policy enhances system efficiency