Multi-attention Network for One Shot Learning

By Peng Wang, Lingqiao Liu, Chunhua Shen, Zi-Liang Huang, Anton van den Hengel, Heng Tao Shen. 2017

86 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

In Meta & Continual Learning

Citations in the corpus

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, background): “Existing works [87], [88] show that once some categories have been learned, the knowledge gained in this process can be abstracted and used to learn novel classes efﬁciently, even if only one learning example per new class is given ( i.e. , via one-shot learning).”
Learning to Reconstruct Shapes from Unseen Classes (2018, background): “More recently, many researchers have begun to study zero- or few-shot recognition with deep networks [Akata et al., 2016, Antol et al., 2014, Hariharan and Girshick, 2017, Wang et al., 2017, Wang and Hebert, 2016].”
Generalizing from a Few Examples (2019, methodology): “owledge in complementary views. The idea of using multi-modality is used in zero-shot learning frequently. They consider prior knowledge including attributes [1, 54], WordNet [1, 54], word embeddings [121, 128] , co-occurrence statistics [77], and knowledge graphs [129]. Recently, there are some wor”
One-Shot Instance Segmentation (2018, background): “The metric learning approach has seen a number of improvements in recent years [36, 84, 79, 85, 86].”
Multi-modal Cycle-consistent Generalized Zero-Shot Learning (2018, methodology): “For CUB, FLO, SUN, and AWA we use the zero-shot splits proposed by Xian et al. [2], making sure that none of the training classes are present on ImageNet [15].”
Small Sample Learning in Big Data Era (2018, methodology): “The former manner tends to generate sample redundancy and encounters the problem of over-fitting to the rare classes, whereas the latter inclines to lose critical feature knowledge within the classes with more samples (Wang et al., 2017c).”
Few-shot learning with adaptively initialized task optimizer: a practical meta-learning approach (2019, methodology): “Meta-learning approaches have been successfully applied in various ﬁelds, like long-tail class-imbalance classiﬁcation (Wang et al. 2017b; Ren et al. 2018), domain adaptation (Motiian et al. 2017; Zhang et al. 2018), intimation learning (Yu et al. 2018), density estimation (Reed et al. 2017),…”
Spot and Learn: A Maximum-Entropy Patch Sampler for Few-Shot Image Classification (2019, methodology): “There has also been some works on using soft attention for Few-Shot Learning using attention generated from semantic information [28, 3].”
Image Deformation Meta-Networks for One-Shot Learning (2019, background): “Attention is also introduced in meta-learning, in ways of analyzing the relation between visual and semantic representations [29] and learning the combination of temporal convolutions and soft attention [14].”
Reinforced Attention for Few-Shot Learning and Beyond (2021, methodology): “Using word embeddings as auxiliary data, semantics-guided attention modules are proposed to capture the relevant visual features among query samples [55, 7, 62].”