LAUSR

NucNormZSL: nuclear norm-based domain adaptation in zero-shot learning

Sign Up to like & get
recommendations!
0 Published in 2021 at "Neural Computing and Applications"

DOI: 10.1007/s00521-021-06461-1

Abstract: The ability of human beings to recognize novel concepts has attracted significant attention in the research community. Zero-shot learning, also known as zero-data learning, seeks to build models that can recognize novel class instances even… read more here.

Keywords: nuclear norm; shot learning; class; zero shot ... See more keywords

Multi-local feature relation network for few-shot learning

Sign Up to like & get
recommendations!
1 Published in 2022 at "Neural Computing and Applications"

DOI: 10.1007/s00521-021-06840-8

Abstract: Recently, few-shot learning has received considerable attention from researchers. Compared to deep learning, which requires abundant data for training, few-shot learning only requires a few labeled samples. Therefore, few-shot learning has been extensively used in… read more here.

Keywords: shot learning; feature; support; local feature ... See more keywords

Critical direction projection networks for few-shot learning

Sign Up to like & get
recommendations!
0 Published in 2021 at "Applied Intelligence"

DOI: 10.1007/s10489-020-02110-7

Abstract: With the development of deep learning, visual systems perform better than human beings in many classification tasks. However, the scarcity of labelled data is the most critical problem in such visual systems. Few-shot learning is… read more here.

Keywords: direction projection; classification; shot learning; critical direction ... See more keywords

Few-shot learning with adaptively initialized task optimizer: a practical meta-learning approach

Sign Up to like & get
recommendations!
0 Published in 2019 at "Machine Learning"

DOI: 10.1007/s10994-019-05838-7

Abstract: Considering the data collection and labeling cost in real-world applications, training a model with limited examples is an essential problem in machine learning, visual recognition, etc. Directly training a model on such few-shot learning (FSL)… read more here.

Keywords: shot learning; meta learning; task; adaptively initialized ... See more keywords

DMH-FSL: Dual-Modal Hypergraph for Few-Shot Learning

Sign Up to like & get
recommendations!
3 Published in 2022 at "Neural Processing Letters"

DOI: 10.1007/s11063-021-10684-7

Abstract: Large scale labeled samples are expensive and difficult to obtain, hence few-shot learning (FSL), only needing a small number of labeled samples, is a dedicated technology. Recently, the graph-based FSL approaches have attracted lots of… read more here.

Keywords: modal hypergraph; hypergraph; dmh fsl; shot learning ... See more keywords

Discriminant Zero-Shot Learning with Center Loss

Sign Up to like & get
recommendations!
0 Published in 2019 at "Cognitive Computation"

DOI: 10.1007/s12559-019-09629-z

Abstract: Current work on zero-shot learning (ZSL) generally does not focus on the discriminative ability of the models, which is important for differentiating between classes since our brain focuses on the discriminating part of the object… read more here.

Keywords: zero shot; discriminant zero; shot learning; center loss ... See more keywords

Active one-shot learning by a deep Q-network strategy

Sign Up to like & get
recommendations!
1 Published in 2020 at "Neurocomputing"

DOI: 10.1016/j.neucom.2019.11.017

Abstract: Abstract One-shot learning has recently attracted growing attention to produce models which can classify significant events from a few or even no labeled examples. In this paper, we introduce a deep Q-network strategy into one-shot… read more here.

Keywords: deep network; network strategy; one shot; shot learning ... See more keywords

Reweighting and information-guidance networks for Few-Shot Learning

Sign Up to like & get
recommendations!
0 Published in 2021 at "Neurocomputing"

DOI: 10.1016/j.neucom.2020.07.128

Abstract: Abstract Few-Shot Learning (FSL) aims at recognizing new categories from a few available samples. In this paper, we propose two strategies on the basis of Prototypical Networks [1] to improve the discriminativeness and representativeness of… read more here.

Keywords: information; shot learning; guidance networks; information guidance ... See more keywords

Few-Shot Learning for Low-Data Drug Discovery

Sign Up to like & get
recommendations!
1 Published in 2022 at "Journal of chemical information and modeling"

DOI: 10.1021/acs.jcim.2c00779

Abstract: The discovery of new hits through ligand-based virtual screening in drug discovery is essentially a low-data problem, as data acquisition is both difficult and expensive. The requirement for large amounts of training data hinders the… read more here.

Keywords: drug discovery; low data; shot; shot learning ... See more keywords

Designing drugs when there is low data availability: one-shot learning and other approaches to face the issues of a long-term concern

Sign Up to like & get
recommendations!
2 Published in 2022 at "Expert Opinion on Drug Discovery"

DOI: 10.1080/17460441.2022.2114451

Abstract: ABSTRACT Introduction Modern drug discovery is generally accessed by useful information from previous large databases or uncovering novel data. The lack of biological and/or chemical data tends to slow the development of scientific research and… read more here.

Keywords: designing drugs; one shot; drugs low; shot learning ... See more keywords

Instance-Level Embedding Adaptation for Few-Shot Learning

Sign Up to like & get
recommendations!
0 Published in 2019 at "IEEE Access"

DOI: 10.1109/access.2019.2906665

Abstract: Few-shot learning aims to recognize novel categories from just a few labeled instances. Existing metric learning-based approaches perform classifications by nearest neighbor search in the embedding space. The embedding function is a deep neural network… read more here.

Keywords: adaptation; instance level; shot learning; instance ... See more keywords