Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts

2025-06-05

AI Summary

To address the degraded prototype concept learning (PCL) performance of self-explaining models (SEMs) in few-shot image classification due to data scarcity, this paper proposes a prototype concept-driven few-shot learning framework targeting two core challenges: parameter imbalance and representation misalignment. We innovatively design a concept-guided Mixture-of-LoRA-Experts mechanism, introduce a geometry-aware concept discrimination loss, and enforce cross-module concept alignment. Furthermore, we integrate multi-level feature extraction, orthogonality constraints, and concept activation guidance to enhance concept fidelity and interpretability. Evaluated on six benchmark datasets under the 5-way 5-shot setting, our method achieves average accuracy improvements of 4.2%–8.7% over state-of-the-art SEMs. It simultaneously delivers strong generalization capability and transparent, human-understandable decision reasoning.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Computer Vision: Interpretability, Explainability, and Transparency
• 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
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable, but they often struggle in data-scarce settings where insufficient training samples lead to suboptimal performance.To address this limitation, we propose a Few-Shot Prototypical Concept Classification (FSPCC) framework that systematically mitigates two key challenges under low-data regimes: parametric imbalance and representation misalignment. Specifically, our approach leverages a Mixture of LoRA Experts (MoLE) for parameter-efficient adaptation, ensuring a balanced allocation of trainable parameters between the backbone and the PCL module.Meanwhile, cross-module concept guidance enforces tight alignment between the backbone's feature representations and the prototypical concept activation patterns.In addition, we incorporate a multi-level feature preservation strategy that fuses spatial and semantic cues across various layers, thereby enriching the learned representations and mitigating the challenges posed by limited data availability.Finally, to enhance interpretability and minimize concept overlap, we introduce a geometry-aware concept discrimination loss that enforces orthogonality among concepts, encouraging more disentangled and transparent decision boundaries.Experimental results on six popular benchmarks (CUB-200-2011, mini-ImageNet, CIFAR-FS, Stanford Cars, FGVC-Aircraft, and DTD) demonstrate that our approach consistently outperforms existing SEMs by a notable margin, with 4.2%-8.7% relative gains in 5-way 5-shot classification.These findings highlight the efficacy of coupling concept learning with few-shot adaptation to achieve both higher accuracy and clearer model interpretability, paving the way for more transparent visual recognition systems.

Problem

• Improves interpretable few-shot image classification performance
• Addresses parametric imbalance and representation misalignment in low-data regimes
• Enhances model interpretability via concept-guided feature alignment

Innovation

• Mixture of LoRA Experts for parameter-efficient adaptation
• Cross-module concept guidance for feature alignment
• Geometry-aware concept discrimination loss for interpretability