Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition

  title={Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition},
  author={Mengting Chen and Xinggang Wang and Heng Luo and Yifeng Geng and Wenyu Liu},
  journal={Sci. China Inf. Sci.},
Generally, deep networks learn to recognize a category of objects by training on a large number of annotated images accurately. However, a meta-learning problem known as a low-shot image recognition task occurs when a few images with annotations are available for learning a recognition model for a single category. Consequently, the objects in testing/query and training/support image datasets are likely to vary in terms of size, location, style, and so on. In this paper, we propose a method… 


Few-Shot Image Recognition by Predicting Parameters from Activations
A novel method that can adapt a pre-trained neural network to novel categories by directly predicting the parameters from the activations is proposed, which achieves the state-of-the-art classification accuracy on Novel categories by a significant margin while keeping comparable performance on the large-scale categories.
Few-Shot Object Detection via Feature Reweighting
This work develops a few-shot object detector that can learn to detect novel objects from only a few annotated examples, using a meta feature learner and a reweighting module within a one-stage detection architecture.
Deep Comparison: Relation Columns for Few-Shot Learning
A new framework termed Deep Comparison Network (DCN) is proposed that decomposes embedding learning into a sequence of modules, and pairs each with a relation module, and achieves state of the art performance on both miniImageNet and tieredImageNet, while retaining the appealing simplicity and efficiency of deep metric learning approaches.
Multi-attention Network for One Shot Learning
A neural network architecture is designed which takes the semantic embedding of the class tag to generate attention maps and uses those attention maps to create the image features for one-shot learning.
A Dual Attention Network with Semantic Embedding for Few-Shot Learning
This work proposes a novel meta-learning method for few-shot classification based on two simple attention mechanisms: one is a spatial attention to localize relevant object regions and the other is a task attention to select similar training data for label prediction.
Image Deformation Meta-Networks for One-Shot Learning
This work combines a meta-learner with an image deformation sub-network that produces additional training examples, and optimize both models in an end-to-end manner to significantly outperform state-of-the-art approaches on widely used one-shot learning benchmarks.
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.
AnchorNet: A Weakly Supervised Network to Learn Geometry-Sensitive Features for Semantic Matching
This work proposes a deep network, termed AnchorNet, that produces image representations that are well-suited for semantic matching that are trained only with weak image-level labels and improves results of state-of-the-art semantic matching methods such as the Deformable Spatial Pyramid or the Proposal Flow methods.
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.
Delta-encoder: an effective sample synthesis method for few-shot object recognition
This work proposes a simple yet effective method for few-shot (and one-shot) object recognition based on a modified auto-encoder that learns to synthesize new samples for an unseen category just by seeing few examples from it.