专题：Domain Adaptation and Few-Shot Learning

This cluster of papers focuses on the advances in transfer learning and domain adaptation, including topics such as few-shot learning, unsupervised learning, representation learning, deep networks, meta-learning, visual recognition, semi-supervised learning, and clustering analysis.
最新文献
Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detection

article Full Text OpenAlex

Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing

article Full Text OpenAlex

MS-CADNet: A Multi-Scale Context Attention Network for Efficient Object Detection in UAV Imagery

article Full Text OpenAlex

Digital twin-assisted graph contrastive domain adaptation for small-sample bearing fault diagnosis

article Full Text OpenAlex

Spatial-channel collaborative multi-scale graph interaction deep transfer learning for unsupervised rotating machinery fault diagnosis

article Full Text OpenAlex

Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning

article Full Text OpenAlex

Autonomous Learning through Self-Driven Exploration and Knowledge Structuring for Open-World Intelligent Agents

article Full Text OpenAlex

Retrieval-augmented in-context learning for multimodal large language models in disease classification

article Full Text OpenAlex

Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models

article Full Text OpenAlex

Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging

article Full Text OpenAlex

近5年高被引文献