paper-with-me

홈 › Papers

Learning to Compare: Relation Network for Few-Shot Learning

2017-11-16 · CVPR 2018 6 · Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip H. S. Torr, Timothy M. Hospedales

We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained end-to-end from scratch. During meta-learning, it learns to learn a deep distance metric to compare a small number of images within episodes, each of which is designed to simulate the few-shot setting. Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network. Besides providing improved performance on few-shot learning, our framework is easily extended to zero-shot learning. Extensive experiments on five benchmarks demonstrate that our simple approach provides a unified and effective approach for both of these two tasks.

📄 PDF Abstract BibTeX arXiv:1711.06025

Code (13)

Atharva-Phatak/One-Shot-Art pytorch
Mind23-2/MindCode-66 mindspore
code-implementation1/Code7/tree/main/relationnet mindspore
flexibility2/Pytorch-Implementation-for-RelationNet pytorch
floodsung/LearningToCompare_FSL pytorch
jiakangyuan/helixformer pytorch
khoiucd/LearningToCompare-Tensorflow tf
knnaraghi/fewshot tf
laohur/LearnToCompareText pytorch
laohur/RelationNet pytorch
lzrobots/LearningToCompare_ZSL pytorch
prolearner/LearningToCompareTF tf
sicara/easy-few-shot-learning pytorch

Tasks

Few-Shot Image ClassificationFew-Shot LearningMeta-LearningRelationRelation NetworkZero-Shot Learning

Similar Papers 제목 키워드 기반

Learning Meta Representations of One-shot Relations for Temporal Knowledge Graph Link Prediction

2022-05-21 · Zifeng Ding, Bailan He, Yunpu Ma, Zhen Han 외

Few-shot relational learning for static knowledge graphs (KGs) has drawn greater interest in recent years, while few-shot learning for temporal knowledge graphs (TKGs) has hardly been studied. Compared to KGs, TKGs conta…

Few-Shot LearningKnowledge GraphsLink PredictionRelational Reasoning

FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation

2018-10-24 · EMNLP 2018 10 · Xu Han, Hao Zhu, Pengfei Yu, ZiYun Wang 외

We present a Few-Shot Relation Classification Dataset (FewRel), consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers. The relation of each sentence is first recognized by …

ClassificationFew-Shot LearningFew-Shot Relation ClassificationGeneral Classification+4

Neural Snowball for Few-Shot Relation Learning

2019-08-29 · Tianyu Gao, Xu Han, Ruobing Xie, Zhiyuan Liu 외

Knowledge graphs typically undergo open-ended growth of new relations. This cannot be well handled by relation extraction that focuses on pre-defined relations with sufficient training data. To address new relations with…

Knowledge GraphsRelationRelation Extraction

Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion

2021-04-27 · Guanglin Niu, Yang Li, Chengguang Tang, Ruiying Geng 외

Aiming at expanding few-shot relations' coverage in knowledge graphs (KGs), few-shot knowledge graph completion (FKGC) has recently gained more research interests. Some existing models employ a few-shot relation's multi-…

Few-Shot LearningKnowledge Graph CompletionKnowledge GraphsMeta-Learning+1

Revisiting Large Language Models as Zero-shot Relation Extractors

2023-10-08 · Guozheng Li, Peng Wang, Wenjun Ke

Relation extraction (RE) consistently involves a certain degree of labeled or unlabeled data even if under zero-shot setting. Recent studies have shown that large language models (LLMs) transfer well to new tasks out-of-…

Question AnsweringRelationRelation Extraction