Enhancing Few-Shot Classification of Benchmark and Disaster Imagery with ATTBHFA-Net

2025-10-21

AI Summary

Limited disaster image data, high intra-class variability, and strong inter-class similarity severely constrain few-shot classification performance. To address these challenges, this paper proposes ATTBHFA-Net—a feature aggregation network integrating attention mechanisms with a Bhattacharyya–Hellinger joint metric. It introduces, for the first time, a distributional contrastive loss that couples the Bhattacharyya coefficient and Hellinger distance, jointly enhancing inter-class separability and intra-class consistency within a distributed contrastive learning framework. Furthermore, it incorporates attention-weighted prototype construction and joint optimization with cross-entropy to improve few-shot robustness. Extensive experiments on four standard few-shot benchmarks and two real-world disaster image datasets demonstrate significant improvements over state-of-the-art methods, validating ATTBHFA-Net’s superior generalization capability and practical deployability in disaster-related applications.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Search and Optimization: Distributed Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The increasing frequency of natural and human-induced disasters necessitates advanced visual recognition techniques capable of analyzing critical photographic data. With progress in artificial intelligence and resilient computational systems, rapid and accurate disaster classification has become crucial for efficient rescue operations. However, visual recognition in disaster contexts faces significant challenges due to limited and diverse data from the difficulties in collecting and curating comprehensive, high-quality disaster imagery. Few-Shot Learning (FSL) provides a promising approach to data scarcity, yet current FSL research mainly relies on generic benchmark datasets lacking remote-sensing disaster imagery, limiting its practical effectiveness. Moreover, disaster images exhibit high intra-class variation and inter-class similarity, hindering the performance of conventional metric-based FSL methods. To address these issues, this paper introduces the Attention-based Bhattacharyya-Hellinger Feature Aggregation Network (ATTBHFA-Net), which linearly combines the Bhattacharyya coefficient and Hellinger distances to compare and aggregate feature probability distributions for robust prototype formation. The Bhattacharyya coefficient serves as a contrastive margin that enhances inter-class separability, while the Hellinger distance regularizes same-class alignment. This framework parallels contrastive learning but operates over probability distributions rather than embedded feature points. Furthermore, a Bhattacharyya-Hellinger distance-based contrastive loss is proposed as a distributional counterpart to cosine similarity loss, used jointly with categorical cross-entropy to significantly improve FSL performance. Experiments on four FSL benchmarks and two disaster image datasets demonstrate the superior effectiveness and generalization of ATTBHFA-Net compared to existing approaches.

Problem

• Addressing few-shot classification challenges in disaster imagery
• Overcoming data scarcity and high intra-class variation in FSL
• Improving prototype formation with distribution-based metric learning

Innovation

• Combining Bhattacharyya coefficient and Hellinger distances
• Aggregating feature probability distributions for robust prototypes
• Using distributional contrastive loss with cross-entropy