Revisiting Mid-Level Patterns for Cross-Domain Few-Shot Recognition
Existing few-shot learning (FSL) methods usually assume base classes and novel classes are from the same domain (in-domain setting). However, in practice, it may be infeasible to collect sufficient training samples for some special domains to construct base classes. To solve this problem, cross-domain FSL (CDFSL) is proposed very recently to transfer knowledge from general-domain base classes to special-domain novel classes. Existing CDFSL works mostly focus on transferring between near domains, while rarely consider transferring between distant domains, which is in practical need as any novel classes could appear in real-world applications, and is even more challenging. In this paper, we study a challenging subset of CDFSL where the novel classes are in distant domains from base classes, by revisiting the mid-level features, which are more transferable yet under-explored in main stream FSL work. To boost the discriminability of mid-level features, we propose a residual-prediction task to encourage mid-level features to learn discriminative information of each sample. Notably, such mechanism also benefits the in-domain FSL and CDFSL in near domains. Therefore, we provide two types of features for both cross- and in-domain FSL respectively, under the same training framework. Experiments under both settings on six public datasets, including two challenging medical datasets, validate the our rationale and demonstrate state-of-the-art performance. Code will be released.
Code (0)
등록된 구현이 없습니다.
Tasks
Cross-Domain Few-Shotcross-domain few-shot learningFew-Shot LearningSimilar Papers 제목 키워드 기반
Revisiting LLMs as Zero-Shot Time-Series Forecasters: Small Noise Can Break Large Models
Large Language Models (LLMs) have shown remarkable performance across diverse tasks without domain-specific training, fueling interest in their potential for time-series forecasting. While LLMs have shown potential in ze…
SensitivityTime SeriesTime Series ForecastingA Zero-Shot Generalization Framework for LLM-Driven Cross-Domain Sequential Recommendation
Zero-shot cross-domain sequential recommendation (ZCDSR) enables predictions in unseen domains without the need for additional training or fine-tuning, making it particularly valuable in data-sparse environments where tr…
Sequential RecommendationTransfer LearningZero-shot GeneralizationRevisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning
Few-shot learning in image classification aims to learn a classifier to classify images when only few training examples are available for each class. Recent work has achieved promising classification performance, where a…
Few-Shot Image ClassificationFew-Shot LearningGeneral Classificationimage-classification+1A Zero-shot Generalized Graph Anomaly Detection Framework via Node Reconstruction
Cross-domain graph anomaly detection (GAD) aims to identify abnormal nodes in unseen target graphs, showing strong potential in real-world applications with heterogeneous graph data. However, existing methods often depen…
Graph Anomaly DetectionRecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation
Recent advances in LLM-based recommendation have shown promise, yet their cross-domain generalization is hindered by a fundamental mismatch between language-centric pretraining and the recommendation task. Existing metho…
Domain Generalization