Corpus ID: 54441050

Cross-Modulation Networks for Few-Shot Learning

@article{Prol2018CrossModulationNF,
  title={Cross-Modulation Networks for Few-Shot Learning},
  author={Hugo Prol and Vincent Dumoulin and Luis Herranz},
  journal={ArXiv},
  year={2018},
  volume={abs/1812.00273}
}
A family of recent successful approaches to few-shot learning relies on learning an embedding space in which predictions are made by computing similarities between examples. This corresponds to combining information between support and query examples at a very late stage of the prediction pipeline. Inspired by this observation, we hypothesize that there may be benefits to combining the information at various levels of abstraction along the pipeline. We present an architecture called Cross… Expand
Reweighting and information-guidance networks for Few-Shot Learning
TLDR
Two strategies on the basis of Prototypical Networks are proposed to improve the discriminativeness and representativeness of the visual prototypes for few-shot learning task and could be seamlessly combined into some existing approaches to substantially improve their performances on few- shot classification. Expand
Improved prototypical networks for few-Shot learning
TLDR
This work proposes an attention-analogous strategy to explore the class distribution information by distributing different weights to samples based on their representativeness and proposes a distance scaling strategy to reduce the intra- class difference while enlarge the inter-class difference. Expand
Meta-Transfer Learning through Hard Tasks
TLDR
This work proposes a novel approach called meta-transfer learning (MTL), which learns to transfer the weights of a deep NN for few-shot learning tasks, and introduces the hard task (HT) meta-batch scheme as an effective learning curriculum of few- shot classification tasks. Expand
Attentive Feature Reuse for Multi Task Meta learning
TLDR
This work develops new algorithms for simultaneous learning of multiple tasks, and for adapting to unseen task/domain distributions within those high-level tasks, using similar architectures based on weighting each feature map of the backbone network, based on its relevance to a particular task. Expand
Learning from Very Few Samples: A Survey
TLDR
This survey extensively review 300+ papers of FSL spanning from the 2000s to 2019 and provides a timely and comprehensive survey for FSL, which categorize FSL approaches into the generative model based and discriminative modelBased kinds in principle, and emphasize particularly on the meta learning based FSL approach. Expand
Deep Object Co-segmentation via Spatial-Semantic Network Modulation
TLDR
A spatial and semantic modulated deep network framework for object co-segmentation that captures the correlations of image feature descriptors via unsupervised learning and proposes a hierarchical second-order pooling module to transform the image features for classification use. Expand
Few- and Zero-Shots Using Meta-Learning On Hierarchical Knowledge Graphs For Fine-Grained Named Entity Typing
  • 2019
Named Entity Typing is an important building block in various Natural Language Processing tasks. Textual entities are complex and hard to label at scale, making automated and noisy approaches theExpand
A Multi-task Learning Framework for Grasping-Position Detection and Few-Shot Classification
TLDR
Results confirm that the proposed multi-task learning framework for few-shot classification using feature vectors from an intermediate layer of a model that detects grasping positions can classify object shapes even when the input image includes multiple objects and the number of images available for training is small. Expand
Domain Conditional Predictors for Domain Adaptation
TLDR
It is argued that a conditional modeling approach in which predictions, in addition of being dependent of the input data, use information relative to the underlying data-generating distribution is more general than current domain adaptation methods since it does not require extra assumptions such as covariate shift. Expand

References

SHOWING 1-10 OF 28 REFERENCES
Prototypical Networks for Few-shot Learning
TLDR
This work proposes Prototypical Networks for few-shot classification, and provides an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. Expand
Learning to Compare: Relation Network for Few-Shot Learning
TLDR
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, which is easily extended to zero- shot learning. Expand
Matching Networks for One Shot Learning
TLDR
This work employs ideas from metric learning based on deep neural features and from recent advances that augment neural networks with external memories to learn a network that maps a small labelled support set and an unlabelled example to its label, obviating the need for fine-tuning to adapt to new class types. Expand
Optimization as a Model for Few-Shot Learning
Meta-Learning for Semi-Supervised Few-Shot Classification
TLDR
This work proposes novel extensions of Prototypical Networks that are augmented with the ability to use unlabeled examples when producing prototypes, and confirms that these models can learn to improve their predictions due to unlabeling examples, much like a semi-supervised algorithm would. Expand
TADAM: Task dependent adaptive metric for improved few-shot learning
TLDR
This work identifies that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms and proposes and empirically test a practical end-to-end optimization procedure based on auxiliary task co-training to learn a task-dependent metric space. Expand
Squeeze-and-Excitation Networks
TLDR
This work proposes a novel architectural unit, which is term the “Squeeze-and-Excitation” (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels and shows that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand
Meta-Learning with Latent Embedding Optimization
TLDR
This work shows that latent embedding optimization can achieve state-of-the-art performance on the competitive miniImageNet and tieredImageNet few-shot classification tasks, and indicates LEO is able to capture uncertainty in the data, and can perform adaptation more effectively by optimizing in latent space. Expand
Probabilistic Model-Agnostic Meta-Learning
TLDR
This paper proposes a probabilistic meta-learning algorithm that can sample models for a new task from a model distribution that is trained via a variational lower bound, and shows how reasoning about ambiguity can also be used for downstream active learning problems. Expand
...
1
2
3
...