Explanation-Guided Training for Cross-Domain Few-Shot Classification

Abstract

Cross-domain few-shot classification task (CD-FSC) combines few-shot classification with the requirement to generalize across domains represented by datasets. This setup faces challenges originating from the limited labeled data in each class and, additionally, from the domain shift between training and test sets. In this paper, we introduce a novel training approach for existing FSC models. It leverages on the explanation scores, obtained from existing explanation methods when applied to the predictions of FSC models, computed for intermediate feature maps of the models. Firstly, we tailor the layer-wise relevance propagation (LRP) method to explain the predictions of FSC models. Secondly, we develop a model-agnostic explanation-guided training strategy that dynamically finds and emphasizes the features which are important for the predictions. Our contribution does not target a novel explanation method but lies in a novel application of explanations for the training phase. We show that explanation-guided training effectively improves the model generalization. We observe improved accuracy for three different FSC models: RelationNet, cross attention network, and a graph neural network-based formulation, on five few-shot learning datasets: miniImagenet, CUB, Cars, Places, and Plantae. The source code is available at https://github.com/SunJiamei/few-shot-lrp-guided

References in corpus (19)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Axiomatic Attribution for Deep Networks
• Learning Important Features Through Propagating Activation Differences
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• A Simple Neural Attentive Meta-Learner
• Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
• Learning how to explain neural networks: PatternNet and PatternAttribution
• "What is Relevant in a Text Document?": An Interpretable Machine Learning Approach
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• Learning to Self-Train for Semi-Supervised Few-Shot Classification
• Cross Attention Network for Few-shot Classification
• Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation
• From Clustering to Cluster Explanations via Neural Networks
• Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classification
• Cross-Domain Few-Shot Learning with Meta Fine-Tuning
• A Broader Study of Cross-Domain Few-Shot Learning
• Boosting Few-Shot Learning With Adaptive Margin Loss
• Large Margin Mechanism and Pseudo Query Set on Cross-Domain Few-Shot Learning

Cited by in corpus (6)

• Region Comparison Network for Interpretable Few-shot Image Classification
• Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
• Cross-Domain Few-Shot Classification via Adversarial Task Augmentation
• Ranking Distance Calibration for Cross-Domain Few-Shot Learning
• Improving the Generalization of Meta-learning on Unseen Domains via Adversarial Shift
• Split and Expand: An inference-time improvement for Weakly Supervised Cell Instance Segmentation