Transductive Propagation Network for Few-shot Learning

By Yanbin Liu, Juho Lee, Minseop Park, Saehoon Kim, Yi Yang. 2018

81 citations recorded by the source corpus.

Subfields: Graph Learning, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Graph Learning

In Meta & Continual Learning

Citations in the corpus

Meta-Learning with Latent Embedding Optimization (2018, neutral): “Nets (Liu et al., 2018) 57 .”
A Baseline for Few-Shot Image Classification (2019, background): “A number of recent approaches such 118 as [15, 2] also perform test-time processing and are expected to be slow.”
Learning to Self-Train for Semi-Supervised Few-Shot Classification (2019, methodology): “We choose a top-performing one – meta-transfer learning (MTL) [30] (for fair comparison we also evaluate this method as a component of other semisupervised methods [22, 37]) that is based on simple and elegant gradient descent optimization [3].”
Boosting Few-Shot Visual Learning With Self-Supervision (2019, neutral): “†: results from [33].”
All you need is a good representation: A multi-level and classifier-centric representation for few-shot learning (2019, unknown): “Meta-learning based methods tackle the few-shot learning problem by training a meta-learner to help a learner can effectively learn a new task on very few training data [12, 15, 12, 17, 6, 8].”
Online Structured Meta-learning (2020, background): “Under this setting, there are two representative lines of meta-learning algorithm, including optimization-based meta-learning [7–9, 13, 11, 17, 19, 26, 28, 31] and nonparametric meta-learning [12, 22, 24, 34, 35, 38, 43].”
Generating Classification Weights With GNN Denoising Autoencoders for Few-Shot Learning (2019, unknown): “74 % RelationNet [42] (from [21]) Conv-4-64 54.”
Edge-Labeling Graph Neural Network for Few-Shot Learning (2019, methodology): “A few approaches [6, 12] have explored GNNs for few-shot learning and are based on the node-labeling framework.”
Learning Embedding Adaptation for Few-Shot Learning (2018, methodology): “In FSL, M is often small ( M = 1 or M = 5 in this work).”
Finding Task-Relevant Features for Few-Shot Learning by Category Traversal (2019, background): “91% [23] on the two benchmarks miniImageNet and tieredImageNet, respectively.”
TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning (2019, background): “78% Transductive Propagation Nets (Liu et al., 2018) 59.”
Improved Few-Shot Visual Classification (2019, unknown): “For comparison to more recent work [8, 21, 26, 32] for which Meta-Dataset evaluations are not available, we use mini/tieredImageNet.”
Adaptive Cross-Modal Few-Shot Learning (2019, methodology): “in (Liu et al., 2019) Model Test Accuracy 1-shot 5-shot MAML† (Finn et al.”