Filters








8,852 Hits in 3.7 sec

Few-Shot One-Class Classification via Meta-Learning [article]

Ahmed Frikha, Denis Krompaß, Hans-Georg Köpken, Volker Tresp
2021 arXiv   pre-print
Although few-shot learning and one-class classification (OCC), i.e., learning a binary classifier with data from only one class, have been separately well studied, their intersection remains rather unexplored  ...  suited for learning few-shot OCC tasks.  ...  Class-balanced few-shot classification Meta-learning approaches for FS classification approaches may be broadly categorized in 2 categories.  ... 
arXiv:2007.04146v2 fatcat:743t776ymva7fnacif7wx7c6qm

Trainable Class Prototypes for Few-Shot Learning [article]

Jianyi Li, Guizhong Liu
2021 arXiv   pre-print
Overall we solve the few-shot tasks in two phases: meta-training a transferable feature extractor via self-supervised learning and training the prototypes for metric classification.  ...  few-shot learning methods.  ...  Overall we solve the few-shot tasks in two phases: meta-training a transferable feature extractor via self-supervised learning and training the prototypes for metric classification.  ... 
arXiv:2106.10846v1 fatcat:jejraksfvjep5jacdrosnrrafq

When Low Resource NLP Meets Unsupervised Language Model: Meta-pretraining Then Meta-learning for Few-shot Text Classification [article]

Shumin Deng, Ningyu Zhang, Zhanlin Sun, Jiaoyan Chen, Huajun Chen
2019 arXiv   pre-print
In such challenging scenarios, recent studies have often used meta-learning to simulate the few-shot task, thus negating implicit common linguistic features across tasks.  ...  It can thus be further suggested that pretraining could be a promising solution for few-shot learning of many other NLP tasks.  ...  To this end, we try to utilize meta-learning method on the training set to extract task-agnostic knowledge, which may perform better for few-shot text classification on the test set.  ... 
arXiv:1908.08788v2 fatcat:mfullotkx5ahbaoqcxn2zk66em

Few-Shot Classification in Unseen Domains by Episodic Meta-Learning Across Visual Domains [article]

Yuan-Chia Cheng, Ci-Siang Lin, Fu-En Yang, Yu-Chiang Frank Wang
2021 arXiv   pre-print
In this paper, we present a unique learning framework for domain-generalized few-shot classification, where base classes are from homogeneous multiple source domains, while novel classes to be recognized  ...  Few-shot classification aims to carry out classification given only few labeled examples for the categories of interest.  ...  Cross-domain episodic meta-learning Metric-learning based meta-learning has been widely applied for solving few-shot classification tasks [8, 9, 10] .  ... 
arXiv:2112.13539v1 fatcat:ziptw3ihhrbbpkznjabtfjxice

When Low Resource NLP Meets Unsupervised Language Model: Meta-Pretraining then Meta-Learning for Few-Shot Text Classification (Student Abstract)

Shumin Deng, Ningyu Zhang, Zhanlin Sun, Jiaoyan Chen, Huajun Chen
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In such challenging scenarios, recent studies have often used meta-learning to simulate the few-shot task, thus negating implicit common linguistic features across tasks.  ...  It can thus be further suggested that pretraining could be a promising solution for few-shot learning of many other NLP tasks.  ...  To this end, we try to utilize meta-learning method on the training set to extract task-agnostic knowledge, which may perform better for few-shot text classification on the test set.  ... 
doi:10.1609/aaai.v34i10.7158 fatcat:u75k5swow5gp5jhhs772orchfe

MetaConcept: Learn to Abstract via Concept Graph for Weakly-Supervised Few-Shot Learning [article]

Baoquan Zhang, Ka-Cheong Leung, Yunming Ye, Xutao Li
2021 arXiv   pre-print
, so as to boost the classification performance of meta-learning on weakly-supervised few-shot learning problems.  ...  We have conducted extensive experiments on two weakly-supervised few-shot learning benchmarks, namely, WS-ImageNet-Pure and WS-ImageNet-Mix.  ...  We then perform meta-learning on the few-shot entity classification tasks to explore transferrable knowledge.  ... 
arXiv:2007.02379v2 fatcat:fzsqgk6btfeq7ayilukdbjop4u

A Concise Review of Recent Few-shot Meta-learning Methods [article]

Xiaoxu Li and Zhuo Sun and Jing-Hao Xue and Zhanyu Ma
2020 arXiv   pre-print
Few-shot meta-learning has been recently reviving with expectations to mimic humanity's fast adaption to new concepts based on prior knowledge.  ...  We conclude this review with some vital current challenges and future prospects in few-shot meta-learning.  ...  Up to present, there are only few domain adaptation proposals for few-shot image classification. Therefore, it merits further exploration on cross-domain few-shot meta-learning.  ... 
arXiv:2005.10953v1 fatcat:v54jrpktazf3bfx4kqos4ls27y

Few-Shot Image Classification via Contrastive Self-Supervised Learning [article]

Jianyi Li, Guizhong Liu
2020 arXiv   pre-print
Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required.  ...  We solve the few-shot tasks in two phases: meta-training a transferable feature extractor via contrastive self-supervised learning and training a classifier using graph aggregation, self-distillation and  ...  Abstract-Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required.  ... 
arXiv:2008.09942v1 fatcat:bj7qyiacqnfnfnd4dqeklyj4li

Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation [article]

Jay Patravali, Gaurav Mittal, Ye Yu, Fuxin Li, Mei Chen
2021 arXiv   pre-print
MetaUVFS comprises a novel Action-Appearance Aligned Meta-adaptation (A3M) module that learns to focus on the action-oriented video features in relation to the appearance features via explicit few-shot  ...  methods on few-shot benchmarks.  ...  Unsupervised Meta-learning for Video Few-Shot (MetaUVFS) MetaUVFS explicitly trains a few-shot meta-learner via episodic training to improve performance on the downstream few-shot tasks having novel classes  ... 
arXiv:2109.15317v2 fatcat:36fm5sd6azhzpdcfr2hoh3lyjm

FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs [article]

Song Wang, Yushun Dong, Xiao Huang, Chen Chen, Jundong Li
2022 arXiv   pre-print
Few-shot graph classification aims at predicting classes for graphs, given limited labeled graphs for each class.  ...  Moreover, a task-specific classifier is proposed to utilize the learned task correlations for few-shot classification.  ...  The latter type of method optimizes the model parameters via gradient descent on few-shot samples such that the model can be quickly generalized to new classes.  ... 
arXiv:2205.02435v2 fatcat:y26iplnxqvhx7hexq7iiffpope

Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning [article]

Wenbin Li, Lei Wang, Jinglin Xu, Jing Huo, Yang Gao, Jiebo Luo
2019 arXiv   pre-print
Few-shot learning in image classification aims to learn a classifier to classify images when only few training examples are available for each class.  ...  Our work leads to a simple, effective, and computationally efficient framework for few-shot learning.  ...  ., via nearest-neighbor search) of the local features of a query image to the pool of each class for classification. Again, this observation applies to few-shot learning.  ... 
arXiv:1903.12290v2 fatcat:yrft43dj2rbcpbvarsjdpm4uv4

Meta-free few-shot learning via representation learning with weight averaging [article]

Kuilin Chen, Chi-Guhn Lee
2022 arXiv   pre-print
Recent studies on few-shot classification using transfer learning pose challenges to the effectiveness and efficiency of episodic meta-learning algorithms.  ...  Transfer learning approaches are a natural alternative, but they are restricted to few-shot classification.  ...  Few-shot classification results We conduct few-shot classification experiments on four widely used few-shot image recognition benchmarks and one cross-domain few-shot learning dataset.  ... 
arXiv:2204.12466v2 fatcat:wspokfsrrjgpbewdgn5ha4offm

Self-Promoted Supervision for Few-Shot Transformer [article]

Bowen Dong, Pan Zhou, Shuicheng Yan, Wangmeng Zuo
2022 arXiv   pre-print
In this work, we empirically find that with the same few-shot learning frameworks, \eg~Meta-Baseline, replacing the widely used CNN feature extractor with a ViT model often severely impairs few-shot classification  ...  Specifically, besides the conventional global supervision for global semantic learning SUN further pretrains the ViT on the few-shot learning dataset and then uses it to generate individual location-specific  ...  learning methods under 5-way few-shot classification setting.  ... 
arXiv:2203.07057v2 fatcat:mjfukvyzubcihds26kfnjerfyi

Coarse-to-Fine Pseudo-Labeling Guided Meta-Learning for Inexactly-Supervised Few-Shot Classification [article]

Jinhai Yang, Hua Yang, Lin Chen
2020 arXiv   pre-print
In this paper, we present a new problem named inexactly-supervised meta-learning to alleviate such limitation, focusing on tackling few-shot classification tasks with only coarse-grained supervision.  ...  Meta-learning has recently emerged as a promising technique to address the challenge of few-shot learning.  ...  [6] ) on the pseudo-labeled few-shot classification tasks generated from the pseudo-fine-classes to excavate transferable knowledge.  ... 
arXiv:2007.05675v2 fatcat:czev6hm2mfep7dascne5fioeza

Few-shot Learning with Meta Metric Learners [article]

Yu Cheng, Mo Yu, Xiaoxiao Guo, Bowen Zhou
2019 arXiv   pre-print
Few-shot Learning aims to learn classifiers for new classes with only a few training examples per class.  ...  Existing meta-learning or metric-learning based few-shot learning approaches are limited in handling diverse domains with various number of labels.  ...  First, we will focus on selecting the data from related domains/resources to support the training of meta metric learners.  ... 
arXiv:1901.09890v1 fatcat:ssekfocxqzdkle6ie7ltw3r34i
« Previous Showing results 1 — 15 out of 8,852 results