paper-with-me

홈 › Papers

Task-Level Contrastiveness for Cross-Domain Few-Shot Learning

2025-10-03 · Kristi Topollai, Anna Choromanska arxiv

Few-shot classification and meta-learning methods typically struggle to generalize across diverse domains, as most approaches focus on a single dataset, failing to transfer knowledge across various seen and unseen domains. Existing solutions often suffer from low accuracy, high computational costs, and rely on restrictive assumptions. In this paper, we introduce the notion of task-level contrastiveness, a novel approach designed to address issues of existing methods. We start by introducing simple ways to define task augmentations, and thereafter define a task-level contrastive loss that encourages unsupervised clustering of task representations. Our method is lightweight and can be easily integrated within existing few-shot/meta-learning algorithms while providing significant benefits. Crucially, it leads to improved generalization and computational efficiency without requiring prior knowledge of task domains. We demonstrate the effectiveness of our approach through different experiments on the MetaDataset benchmark, where it achieves superior performance without additional complexity.

📄 PDF Abstract BibTeX arXiv:2510.03509

Code (0)

등록된 구현이 없습니다.

Tasks

cross-domain few-shot learningComputational Efficiency

Similar Papers 제목 키워드 기반

Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming

2021-11-20 · Yizhen Zheng, Ming Jin, Shirui Pan, Yuan-Fang Li 외

Graph representation learning (GRL) is critical for graph-structured data analysis. However, most of the existing graph neural networks (GNNs) heavily rely on labeling information, which is normally expensive to obtain i…

Contrastive LearningGraph Representation LearningRepresentation LearningSelf-Supervised Learning

CASPR: Automated Evaluation Metric for Contrastive Summarization

2024-04-23 · Nirupan Ananthamurugan, Dat Duong, Philip George, Ankita Gupta 외

Summarizing comparative opinions about entities (e.g., hotels, phones) from a set of source reviews, often referred to as contrastive summarization, can considerably aid users in decision making. However, reliably measur…

Decision MakingNatural Language Inference

Vision Transformer for Contrastive Clustering

2022-06-26 · Hua-Bao Ling, Bowen Zhu, Dong Huang, Ding-Hua Chen 외

Vision Transformer (ViT) has shown its advantages over the convolutional neural network (CNN) with its ability to capture global long-range dependencies for visual representation learning. Besides ViT, contrastive learni…

ClusteringContrastive LearningDeep ClusteringImage Clustering+2

Cross-Domain Few-Shot Learning by Representation Fusion

2020-10-13 · Thomas Adler, Johannes Brandstetter, Michael Widrich, Andreas Mayr 외

In order to quickly adapt to new data, few-shot learning aims at learning from few examples, often by using already acquired knowledge. The new data often differs from the previously seen data due to a domain shift, that…

Cross-Domain Few-Shotcross-domain few-shot learningDrug DiscoveryFew-Shot Learning

Multi-level Relation Learning for Cross-domain Few-shot Hyperspectral Image Classification

2023-11-02 · Chun Liu, Longwei Yang, Zheng Li, Wei Yang 외

Cross-domain few-shot hyperspectral image classification focuses on learning prior knowledge from a large number of labeled samples from source domains and then transferring the knowledge to the tasks which contain few l…

ClassificationContrastive LearningCross-Domain Few-Shotcross-domain few-shot learning+5