PEdger++: Practical Edge Detection via Assembling Cross Information

2025-08-16

AI Summary

To address the challenge of simultaneously achieving high accuracy and low computational complexity in edge detection, this paper proposes PEdger++, a lightweight collaborative learning framework that enhances small-model performance without relying on large foundation models. Methodologically, it innovatively integrates diversity across three dimensions: cross-model (heterogeneous architectures), cross-temporal (momentum-based knowledge distillation and multi-stage feature aggregation), and cross-parameter (stochastic parameter sampling and ensemble). This enables efficient feature extraction and synergistic knowledge transfer. Through lightweight architectural design and inference optimization, PEdger++ achieves state-of-the-art performance among lightweight methods on BSDS500, NYUD, and Multicue. It offers multiple computational variants, demonstrating superior accuracy-efficiency trade-offs and strong deployment adaptability across diverse hardware resource constraints.

Technology Category

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

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Edge detection serves as a critical foundation for numerous computer vision applications, including object detection, semantic segmentation, and image editing, by extracting essential structural cues that define object boundaries and salient edges. To be viable for broad deployment across devices with varying computational capacities, edge detectors shall balance high accuracy with low computational complexity. While deep learning has evidently improved accuracy, they often suffer from high computational costs, limiting their applicability on resource-constrained devices. This paper addresses the challenge of achieving that balance: extit{i.e.}, {how to efficiently capture discriminative features without relying on large-size and sophisticated models}. We propose PEdger++, a collaborative learning framework designed to reduce computational costs and model sizes while improving edge detection accuracy. The core principle of our PEdger++ is that cross-information derived from heterogeneous architectures, diverse training moments, and multiple parameter samplings, is beneficial to enhance learning from an ensemble perspective. Extensive experimental results on the BSDS500, NYUD and Multicue datasets demonstrate the effectiveness of our approach, both quantitatively and qualitatively, showing clear improvements over existing methods. We also provide multiple versions of the model with varying computational requirements, highlighting PEdger++'s adaptability with respect to different resource constraints. Codes are accessible at https://github.com/ForawardStar/EdgeDetectionviaPEdgerPlus/.

Problem

• Balance edge detection accuracy and computational complexity
• Reduce computational costs and model sizes efficiently
• Enhance learning via cross-information from heterogeneous architectures

Innovation

• Collaborative learning framework for edge detection
• Utilizes cross-information from heterogeneous architectures
• Multiple model versions for varying resource constraints