AMD-HookNet++: Evolution of AMD-HookNet with Hybrid CNN-Transformer Feature Enhancement for Glacier Calving Front Segmentation

2025-12-16

AI Summary

To address low segmentation accuracy, severe edge jagging, and the difficulty of jointly modeling long-range contextual dependencies and fine-grained local details in glacier calving front delineation from SAR imagery, this paper proposes a CNN-Transformer dual-branch collaborative network. We design an enhanced spatial-channel joint attention module to enable dynamic cross-modal feature fusion, and introduce a pixel-wise contrastive deep supervision mechanism to improve boundary localization robustness. Evaluated on the CaFFe benchmark, our method achieves state-of-the-art performance with IoU = 78.2%, HD95 = 1318 m, and MDE = 367 m. It significantly enhances calving front contour smoothness and geometric fidelity, yielding high-precision, interpretable segmentation results. This advancement provides a reliable foundation for operational glacier dynamics monitoring.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

The dynamics of glaciers and ice shelf fronts significantly impact the mass balance of ice sheets and coastal sea levels. To effectively monitor glacier conditions, it is crucial to consistently estimate positional shifts of glacier calving fronts. AMD-HookNet firstly introduces a pure two-branch convolutional neural network (CNN) for glacier segmentation. Yet, the local nature and translational invariance of convolution operations, while beneficial for capturing low-level details, restricts the model ability to maintain long-range dependencies. In this study, we propose AMD-HookNet++, a novel advanced hybrid CNN-Transformer feature enhancement method for segmenting glaciers and delineating calving fronts in synthetic aperture radar images. Our hybrid structure consists of two branches: a Transformer-based context branch to capture long-range dependencies, which provides global contextual information in a larger view, and a CNN-based target branch to preserve local details. To strengthen the representation of the connected hybrid features, we devise an enhanced spatial-channel attention module to foster interactions between the hybrid CNN-Transformer branches through dynamically adjusting the token relationships from both spatial and channel perspectives. Additionally, we develop a pixel-to-pixel contrastive deep supervision to optimize our hybrid model by integrating pixelwise metric learning into glacier segmentation. Through extensive experiments and comprehensive quantitative and qualitative analyses on the challenging glacier segmentation benchmark dataset CaFFe, we show that AMD-HookNet++ sets a new state of the art with an IoU of 78.2 and a HD95 of 1,318 m, while maintaining a competitive MDE of 367 m. More importantly, our hybrid model produces smoother delineations of calving fronts, resolving the issue of jagged edges typically seen in pure Transformer-based approaches.

Problem

• Segment glacier calving fronts in SAR images for monitoring.
• Enhance segmentation with hybrid CNN-Transformer to capture long-range dependencies.
• Improve edge smoothness in calving front delineations over pure methods.

Innovation

• Hybrid CNN-Transformer architecture for glacier segmentation
• Enhanced spatial-channel attention module for feature interaction
• Pixel-to-pixel contrastive deep supervision for optimization