• Corpus ID: 211678309

Learning to Compare Relation: Semantic Alignment for Few-Shot Learning

@article{Cao2020LearningTC,
  title={Learning to Compare Relation: Semantic Alignment for Few-Shot Learning},
  author={Congqi Cao and Yanning Zhang},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.00210}
}
Few-shot learning is a fundamental and challenging problem since it requires recognizing novel categories from only a few examples. The objects for recognition have multiple variants and can locate anywhere in images. Directly comparing query images with example images can not handle content misalignment. The representation and metric for comparison are critical but challenging to learn due to the scarcity and wide variation of the samples in few-shot learning. In this paper, we present a novel… 

Figures and Tables from this paper

Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification
  • Yike Wu, Bo Zhang, +4 authors Jiayuan Fan
  • Computer Science
    ACM Multimedia
  • 2021
TLDR
This work proposes an object-aware long-short-range spatial alignment approach, which is composed of a foreground object feature enhancement (FOE) module, a long-range semantic correspondence (LSC) module and a short-rangeatial manipulation (SSM) module that is developed to weaken background disturbance and encourage higher foreground object response.
Robust Compare Network for Few-Shot Learning
TLDR
This work argues that it is desirable to learn a robust encoder that can draw inferences about other cases from one example, and improves the accuracy of few-shot learning by mining the internal mechanism of deep networks, which can leverage label information more effectively.

References

SHOWING 1-10 OF 66 REFERENCES
ImageNet Large Scale Visual Recognition Challenge
TLDR
The creation of this benchmark dataset and the advances in object recognition that have been possible as a result are described, and the state-of-the-art computer vision accuracy with human accuracy is compared.
Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions
TLDR
This paper proposes a novel approach to adapt the instance embeddings to the target classification task with a set-to-set function, yielding embeddeddings that are task-specific and are discriminative.
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.
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.
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.
Meta-Learning with Memory-Augmented Neural Networks
TLDR
The ability of a memory-augmented neural network to rapidly assimilate new data, and leverage this data to make accurate predictions after only a few samples is demonstrated.
The Caltech-UCSD Birds-200-2011 Dataset
CUB-200-2011 is an extended version of CUB-200 [7], a challenging dataset of 200 bird species. The extended version roughly doubles the number of images per category and adds new part localization
Deeply Supervised Discriminative Learning for Adversarial Defense
TLDR
This work proposes to class-wise disentangle the intermediate feature representations of deep networks, specifically forcing the features for each class to lie inside a convex polytope that is maximally separated from the polytopes of other classes.
A Two-Stage Approach to Few-Shot Learning for Image Recognition
TLDR
The proposed multi-layer neural network architecture encodes transferable knowledge extracted from a large annotated dataset of base categories and is applied to novel categories containing only a few samples, which produces competitive performance compared to previous work.
Learning to Forget for Meta-Learning
TLDR
This work proposes task-and-layer-wise attenuation on the compromised initialization of model-agnostic meta-learning to reduce its influence and names the method as L2F (Learn to Forget).
...
1
2
3
4
5
...