• Corpus ID: 67749964

Adaptive Cross-Modal Few-Shot Learning

@inproceedings{Xing2019AdaptiveCF,
  title={Adaptive Cross-Modal Few-Shot Learning},
  author={Chen Xing and Negar Rostamzadeh and Boris N. Oreshkin and Pedro H. O. Pinheiro},
  booktitle={NeurIPS},
  year={2019}
}
Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic feature spaces have different structures by definition. For certain concepts, visual features might be richer and more discriminative than text ones. While for others, the inverse might be true. Moreover, when the support from visual information is limited in… 
Learning Class Prototypes Via Anisotropic Combination of Aligned Modalities for Few-Shot Learning
TLDR
It is argued that proper alignment method is important to improve the performance of cross-modal methods, as query data only has visual information in the few-shot learning tasks.
Shaping Visual Representations with Attributes for Few-Shot Learning
TLDR
This work proposes attribute-shaped learning (ASL), which can normalize visual representations to predict attributes for query images and devise an attribute-visual attention module (AVAM), which utilizes attributes to generate more discriminative features.
Feature Transformation Network for Few-Shot Learning
TLDR
An attention-based affinity matrix is introduced to transform the semantical enhanced embedding vectors of query samples by associating the support set, thereby guiding the network to learn a sample representation that embodies higher semantic information in the target area.
Few-shot Learning with Contextual Cueing for Object Recognition in Complex Scenes
TLDR
This work proposes a Class-conditioned Context Attention Module (CCAM) that learns to weight the most important context elements while learning a particular concept and proposes a flexible gating mechanism to ground visual class representations in context semantics.
Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning
TLDR
This work proposes a variance-sensitive class of models that operate in a low-label regime and employs a hierarchically regularized Mahalanobis-distance based classifier combined with a state of the art neural adaptive feature extractor to achieve strong performance on Meta-Dataset, mini-Image net and tiered-ImageNet benchmarks.
Prototype Completion for Few-Shot Learning
TLDR
A novel prototype completion based meta-learning framework that introduces primitive knowledge and extracts representative features for seen attributes as priors and develops a Gaussian based prototype fusion strategy that fuses the mean-based and completed prototypes by exploiting the unlabeled samples.
Weakly-supervised Compositional FeatureAggregation for Few-shot Recognition
TLDR
The simple yet powerful Compositional Feature Aggregation module is presented as a weakly-supervised regularization for deep networks that can be conveniently plugged into existing models for end-to-end optimization while keeping the model size and computation cost nearly the same.
Pseudo Shots: Few-Shot Learning with Auxiliary Data
TLDR
A masking module is proposed that adjusts the features of auxiliary data to be more similar to those of the target classes and can improve accuracy by up to 18 accuracy points, particularly when the auxiliary data is semantically distant from the target task.
Learning from Few Samples: A Survey
TLDR
This paper provides a taxonomy for the techniques and categorize them as data-augmentation, embedding, optimization and semantics based learning for few-shot, one-shot and zero-shot settings, and describes the seminal work done in each category and discusses their approach towards solving the predicament of learning from few samples.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 71 REFERENCES
Learning Robust Visual-Semantic Embeddings
TLDR
An end-to-end learning framework that is able to extract more robust multi-modal representations across domains and a novel technique of unsupervised-data adaptation inference is introduced to construct more comprehensive embeddings for both labeled and unlabeled data.
Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
TLDR
This work proposes a model where a shared latent space of image features and class embeddings is learned by modality-specific aligned variational autoencoders, and align the distributions learned from images and from side-information to construct latent features that contain the essential multi-modal information associated with unseen classes.
Learning Compositional Representations for Few-Shot Recognition
TLDR
This work introduces a simple regularization technique that allows the learned representation to be decomposable into parts, and demonstrates the value of compositional representations on three datasets and shows that they require fewer examples to learn classifiers for novel categories.
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.
Discriminative k-shot learning using probabilistic models
TLDR
It is shown that even a simple probabilistic model achieves state-of-the-art on a standard k-shot learning dataset by a large margin and is able to accurately model uncertainty, leading to well calibrated classifiers, and is easily extensible and flexible, unlike many recent approaches to k- shot learning.
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.
Zero-Shot Learning Through Cross-Modal Transfer
TLDR
This work introduces a model that can recognize objects in images even if no training data is available for the object class, and uses novelty detection methods to differentiate unseen classes from seen classes.
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.
Low-Shot Learning from Imaginary Data
TLDR
This work builds on recent progress in meta-learning by combining a meta-learner with a "hallucinator" that produces additional training examples, and optimizing both models jointly, yielding state-of-the-art performance on the challenging ImageNet low-shot classification benchmark.
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.
...
1
2
3
4
5
...