Filters








13,017 Hits in 5.3 sec

Learning to Compare Relation: Semantic Alignment for Few-Shot Learning [article]

Congqi Cao, Yanning Zhang
2022 arXiv   pre-print
In this paper, we present a novel semantic alignment model to compare relations, which is robust to content misalignment.  ...  We propose to add two key ingredients to existing few-shot learning frameworks for better feature and metric learning ability.  ...  CONCLUSION In order to address content misalignment for few-shot learning, we propose a novel semantic alignment model with multiple streams to compare relations as well as for better representation and  ... 
arXiv:2003.00210v2 fatcat:ukrrdupfvnhpzbhviuqqfxtf7m

Learning to Compare: Relation Network for Few-Shot Learning [article]

Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip H.S. Torr, Timothy M. Hospedales
2018 arXiv   pre-print
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.  ...  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.  ...  Specifically, we propose a two-branch Relation Network (RN) that performs few-shot recognition by learning to compare query images against few-shot labeled sample images.  ... 
arXiv:1711.06025v2 fatcat:twnofghsn5ei5cgn5c2ckocila

Learning to Compare: Relation Network for Few-Shot Learning

Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip H.S. Torr, Timothy M. Hospedales
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
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.  ...  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.  ...  Specifically, we propose a two-branch Relation Network (RN) that performs few-shot recognition by learning to compare query images against few-shot labeled sample images.  ... 
doi:10.1109/cvpr.2018.00131 dblp:conf/cvpr/SungYZXTH18 fatcat:pkiobneolfcblg47ne5p3shbku

Transfer Learning for Aided Target Recognition: Comparing Deep Learning to other Machine Learning Approaches [article]

Samuel Rivera, Olga Mendoza-Schrock, Ashley Diehl
2020 arXiv   pre-print
Our goal is to address this shortcoming by comparing transfer learning within a DL framework to other ML approaches across transfer tasks and datasets.  ...  While TL for classification has been an active area of machine learning (ML) research for decades, transfer learning within a deep learning framework remains a relatively new area of research.  ...  ACKNOWLEDGMENTS We would like to thank Ms. Nicole Robinson for her preliminary work on SVM and other techniques for transfer learning, Mr.  ... 
arXiv:2011.12762v1 fatcat:7rfezonqszctfotyonkcuybtse

Neural relation extraction: a survey [article]

Mehmet Aydar and Ozge Bozal and Furkan Ozbay
2020 arXiv   pre-print
Neural relation extraction discovers semantic relations between entities from unstructured text using deep learning methods.  ...  In this study, we present a comprehensive review of methods on neural network based relation extraction.  ...  We list some studies related to few-shot learning for relation extraction in Table 4 . For the purpose of experimenting few-shot learning algorithms for relation extraction, Han et al.  ... 
arXiv:2007.04247v1 fatcat:xxrcy2ef75dk5aeijqlf6tjgke

Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection [article]

Chenchen Zhu, Fangyi Chen, Uzair Ahmed, Zhiqiang Shen, Marios Savvides
2021 arXiv   pre-print
As a result, our few-shot detector, termed SRR-FSD, is robust and stable to the variation of shots of novel objects.  ...  Few-shot object detection is an imperative and long-lasting problem due to the inherent long-tail distribution of real-world data.  ...  Relation Reasoning The semantic space projection learns to align the concepts from the visual space with the semantic space.  ... 
arXiv:2103.01903v2 fatcat:vluyswfeencnrmdfhsa3f2p5bq

Neural relation extraction: a review

2020 Turkish Journal of Electrical Engineering and Computer Sciences  
Neural relation extraction discovers semantic relations between entities from unstructured text using deep 3 learning methods.  ...  However, recent research studies make use 23 of data-driven deep learning methods, eliminating conventional NLP approaches for relation extraction.  ...  We list some studies related to few-shot learning for relation extraction in Table 4 . For Table 4 .  ... 
doi:10.3906/elk-2005-119 fatcat:o36duadbunhmbesuyayc5jfmxe

Relational Generalized Few-Shot Learning [article]

Xiahan Shi, Leonard Salewski, Martin Schiegg, Zeynep Akata, Max Welling
2020 arXiv   pre-print
Instead, we consider the extended setup of generalized few-shot learning (GFSL), where the model is required to perform classification on the joint label space consisting of both previously seen and novel  ...  Transferring learned models to novel tasks is a challenging problem, particularly if only very few labeled examples are available.  ...  TGG: Transferable graph generation for zero-shot and few-shot learning.  ... 
arXiv:1907.09557v2 fatcat:lzmwzrkupvbj5gljruejozt7xu

Hybrid Relation Guided Set Matching for Few-shot Action Recognition [article]

Xiang Wang, Shiwei Zhang, Zhiwu Qing, Mingqian Tang, Zhengrong Zuo, Changxin Gao, Rong Jin, Nong Sang
2022 arXiv   pre-print
Current few-shot action recognition methods reach impressive performance by learning discriminative features for each video via episodic training and designing various temporal alignment strategies.  ...  By this means, the proposed HyRSM can be highly informative and flexible to predict query categories under the few-shot settings.  ...  Acknowledgment This work is supported by the National Natural Science Foundation of China under grant 61871435, Fundamental Research Funds for the Central Universities no.2019kfyXKJC024, 111 Project on  ... 
arXiv:2204.13423v1 fatcat:dpgf2ntdmfgilpjtfoukwebsmi

Preserving Semantic Relations for Zero-Shot Learning

Soma Biswas, Yashas Annadani
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Through extensive experimental evaluation on five benchmark datasets, we demonstrate that inducing semanticity to the embedding space is beneficial for zero-shot learning.  ...  Zero-shot learning has gained popularity due to its potential to scale recognition models without requiring additional training data.  ...  The authors would like to thank Devraj Mandal of IISc for helpful discussions.  ... 
doi:10.1109/cvpr.2018.00793 dblp:conf/cvpr/AnnadaniB18 fatcat:3lqjy4reqjf37hjn7yyufhgshu

Preserving Semantic Relations for Zero-Shot Learning [article]

Yashas Annadani, Soma Biswas
2018 arXiv   pre-print
Through extensive experimental evaluation on five benchmark datasets, we demonstrate that inducing semanticity to the embedding space is beneficial for zero-shot learning.  ...  Zero-shot learning has gained popularity due to its potential to scale recognition models without requiring additional training data.  ...  The authors would like to thank Devraj Mandal of IISc for helpful discussions.  ... 
arXiv:1803.03049v1 fatcat:kjz5nyrur5apbdtt7445yh3i7y

Pre-training to Match for Unified Low-shot Relation Extraction [article]

Fangchao Liu, Hongyu Lin, Xianpei Han, Boxi Cao, Le Sun
2022 arXiv   pre-print
paradigm to learn few-shot instance summarizing ability.  ...  Low-shot relation extraction~(RE) aims to recognize novel relations with very few or even no samples, which is critical in real scenario application.  ...  Acknowledgements We thank all reviewers for their insightful suggestions.  ... 
arXiv:2203.12274v1 fatcat:t62wsq2dvjecldjpwpk67i3d6a

Prototypical Representation Learning for Relation Extraction [article]

Ning Ding, Xiaobin Wang, Yao Fu, Guangwei Xu, Rui Wang, Pengjun Xie, Ying Shen, Fei Huang, Hai-Tao Zheng, Rui Zhang
2021 arXiv   pre-print
and few-shot learning.  ...  Instead of solely relying on the supervision from noisy labels, we propose to learn prototypes for each relation from contextual information to best explore the intrinsic semantics of relations.  ...  training algorithm for few-shot relation learning.  ... 
arXiv:2103.11647v1 fatcat:zijrpsbi5jbklm2lehay5ky4gy

Relational Embedding for Few-Shot Classification [article]

Dahyun Kang, Heeseung Kwon, Juhong Min, Minsu Cho
2021 arXiv   pre-print
We propose to address the problem of few-shot classification by meta-learning "what to observe" and "where to attend" in a relational perspective.  ...  Our Relational Embedding Network (RENet) combines the two relational modules to learn relational embedding in an end-to-end manner.  ...  (IO201208-07822-01) and the IITP grants (No.2019-0-01906, AI Graduate School Program -POSTECH) (No.2021-0-00537, Visual common sense through self-supervised learning for restoration of invisible parts  ... 
arXiv:2108.09666v1 fatcat:2rme4mbmgrfqdmaf7oubxqejaq

More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction [article]

Xu Han, Tianyu Gao, Yankai Lin, Hao Peng, Yaoliang Yang, Chaojun Xiao, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou
2020 arXiv   pre-print
In order to extract these facts from text, people have been working on relation extraction (RE) for years.  ...  , efficiently learn more relations, easily handle more complicated context, and flexibly generalize to more open domains.  ...  Acknowledgments This work is supported by the Natural Science Foundation of China (NSFC) and the German Research Foundation (DFG) in Project Crossmodal Learning, NSFC 61621136008 / DFG TRR-169, and Beijing  ... 
arXiv:2004.03186v3 fatcat:old3zax3fjauvf5fgsvjwakv2i
« Previous Showing results 1 — 15 out of 13,017 results