EdgePoint2: Compact Descriptors for Superior Efficiency and Accuracy

2025-04-24

AI Summary

To address the challenge of jointly optimizing efficiency, accuracy, and communication overhead in lightweight keypoint detection and descriptor generation for edge-vision tasks, this paper proposes a compact descriptor learning framework based on hyperspherical embedding distillation. Our method introduces a joint optimization objective combining orthogonal Procrustes loss and similarity-preserving loss to enable end-to-end training of highly discriminative, low-dimensional descriptors (32/48/64 dimensions). We design a lightweight neural architecture with 14 scalable sub-models to accommodate diverse edge deployment constraints. Evaluated on multiple standard benchmarks, our approach achieves state-of-the-art accuracy and inference efficiency—yielding significant improvements in real-time performance, robustness under domain shifts, and communication efficiency for distributed edge vision systems.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

The field of keypoint extraction, which is essential for vision applications like Structure from Motion (SfM) and Simultaneous Localization and Mapping (SLAM), has evolved from relying on handcrafted methods to leveraging deep learning techniques. While deep learning approaches have significantly improved performance, they often incur substantial computational costs, limiting their deployment in real-time edge applications. Efforts to create lightweight neural networks have seen some success, yet they often result in trade-offs between efficiency and accuracy. Additionally, the high-dimensional descriptors generated by these networks poses challenges for distributed applications requiring efficient communication and coordination, highlighting the need for compact yet competitively accurate descriptors. In this paper, we present EdgePoint2, a series of lightweight keypoint detection and description neural networks specifically tailored for edge computing applications on embedded system. The network architecture is optimized for efficiency without sacrificing accuracy. To train compact descriptors, we introduce a combination of Orthogonal Procrustes loss and similarity loss, which can serve as a general approach for hypersphere embedding distillation tasks. Additionally, we offer 14 sub-models to satisfy diverse application requirements. Our experiments demonstrate that EdgePoint2 consistently achieves state-of-the-art (SOTA) accuracy and efficiency across various challenging scenarios while employing lower-dimensional descriptors (32/48/64). Beyond its accuracy, EdgePoint2 offers significant advantages in flexibility, robustness, and versatility. Consequently, EdgePoint2 emerges as a highly competitive option for visual tasks, especially in contexts demanding adaptability to diverse computational and communication constraints.

Problem

• Develop lightweight keypoint detection for edge computing efficiency
• Balance accuracy and computational cost in deep learning models
• Create compact descriptors for distributed vision applications

Innovation

• Lightweight neural networks for edge computing
• Orthogonal Procrustes and similarity loss training
• Compact descriptors with 32/48/64 dimensions