• Corpus ID: 102351185

A Closer Look at Few-shot Classification

@article{Chen2019ACL,
  title={A Closer Look at Few-shot Classification},
  author={Wei-Yu Chen and Yen-Cheng Liu and Zsolt Kira and Y. Wang and Jia-Bin Huang},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.04232}
}
Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples. [] Key Method In this paper, we present 1) a consistent comparative analysis of several representative few-shot classification algorithms, with results showing that deeper backbones significantly reduce the performance differences among methods on datasets with limited domain differences, 2) a modified baseline method that surprisingly achieves competitive performance when compared…

Figures and Tables from this paper

A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark

This paper proposes a simple classifier-based baseline without any temporal alignment that surprisingly outperforms the state-of-the-art meta-learning based methods and presents a new benchmark with more base data to facilitate future few-shot video classification without pre-training.

A Baseline for Few-Shot Image Classification

This work performs extensive studies on benchmark datasets to propose a metric that quantifies the "hardness" of a few-shot episode and finds that using a large number of meta-training classes results in high few- shot accuracies even for a largeNumber of few-shots classes.

A Universal Representation Transformer Layer for Few-Shot Image Classification

A Universal Representation Transformer (URT) layer is proposed, that meta-learns to leverage universal features for few-shot classification by dynamically re-weighting and composing the most appropriate domain-specific representations.

Meta Generalized Network for Few-Shot Classification

This paper develops a meta backbone training method that learns a flexible feature extractor and a classifier initializer efficiently, delightedly leading to fast adaption to unseen few-shot tasks without overfitting, and designs a trainable adaptive interval model to improve the cosine classifier, which increases the recognition accuracy of hard examples.

What Makes for Effective Few-shot Point Cloud Classification?

A novel plug-and-play component called Cross-Instance Adaptation (CIA) module is proposed, to address the high intra-class variances and subtle inter-class differences issues, which can be easily inserted into current baselines with significant performance improvement.

Region Comparison Network for Interpretable Few-shot Image Classification

A metric learning based method named Region Comparison Network (RCN) is proposed, able to reveal how few-shot learning works as in a neural network as well as to find out specific regions that are related to each other in images coming from the query and support sets.

Boosting Few-Shot Classification with View-Learnable Contrastive Learning

This work introduces the contrastive loss into few-shot classification for learning latent fine-grained structure in the embedding space and develops a learning-to-learn algorithm to automatically generate different views of the same image.

Revisiting Fine-tuning for Few-shot Learning

In this study, it is shown that in the commonly used low-resolution mini-ImageNet dataset, the fine-tuning method achieves higher accuracy than common few-shot learning algorithms in the 1-shot task and nearly the same accuracy as that of the state-of-the-art algorithm in the 5- shot task.

Looking Wider for Better Adaptive Representation in Few-Shot Learning

The Cross Non-Local Neural Network (CNL) is proposed for capturing the long-range dependency of the samples and the current task, and extracts the task-specific and context-aware features dynamically by strengthening the features of the sample at a position via aggregating information from all positions of itself and theCurrent task.

Novelty-Prepared Few-Shot Classification

This work proposes to use a novelty-prepared loss function, called self-compacting softmax loss (SSL), for few-shot classification, and shows that SSL leads to significant improvement of the state-of-the-art performance.
...

References

SHOWING 1-10 OF 33 REFERENCES

Learning to Compare: Relation Network for Few-Shot Learning

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.

Few-Shot Learning with Metric-Agnostic Conditional Embeddings

This work introduces a novel architecture where class representations are conditioned for each few-shot trial based on a target image, and deviates from traditional metric-learning approaches by training a network to perform comparisons between classes rather than relying on a static metric comparison.

Prototypical Networks for Few-shot Learning

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.

Optimization as a Model for Few-Shot Learning

Matching Networks for One Shot Learning

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.

Dynamic Few-Shot Visual Learning Without Forgetting

This work proposes to extend an object recognition system with an attention based few-shot classification weight generator, and to redesign the classifier of a ConvNet model as the cosine similarity function between feature representations and classification weight vectors.

Siamese Neural Networks for One-Shot Image Recognition

A method for learning siamese neural networks which employ a unique structure to naturally rank similarity between inputs and is able to achieve strong results which exceed those of other deep learning models with near state-of-the-art performance on one-shot classification tasks.

Domain Adaption in One-Shot Learning

This paper proposes a domain adaption framework based on adversarial networks, generalized for situations where the source and target domain have different labels, and uses a policy network, inspired by human learning behaviors, to effectively select samples from the source domain in the training process.

Few-Shot Adversarial Domain Adaptation

This work provides a framework for addressing the problem of supervised domain adaptation with deep models by carefully designing a training scheme whereby the typical binary adversarial discriminator is augmented to distinguish between four different classes.

Deep transfer metric learning

This paper proposes a new deep transfer metric learning (DTML) method to learn a set of hierarchical nonlinear transformations for cross-domain visual recognition by transferring discriminative knowledge from the labeled source domain to the unlabeled target domain.