DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover’s Distance and Structured Classifiers

By Chi Zhang, Yujun Cai, Guosheng Lin, Chunhua Shen. 2020

903 citations recorded by the source corpus.

In this paper, we address the few-shot classification task from a new perspective of optimal matching between image regions. We adopt the Earth Mover's Distance (EMD) as a metric to compute a structural distance between dense image representations to determine image relevance. The EMD generates the optimal matching flows between structural elements that have the minimum matching cost, which is used to represent the image distance for classification. To generate the important weights of elements in the EMD formulation, we design a cross-reference mechanism, which can effectively minimize the impact caused by the cluttered background and large intra-class appearance variations. To handle k-shot classification, we propose to learn a structured fully connected layer that can directly classify dense image representations with the EMD. Based on the implicit function theorem, the EMD can be inserted as a layer into the network for end-to-end training. We conduct comprehensive experiments to validate our algorithm and we set new state-of-the-art performance on four popular few-shot classification benchmarks, namely miniImageNet, tieredImageNet, Fewshot-CIFAR100 (FC100) and Caltech-UCSD Birds-200-2011 (CUB).

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Han-Jia Ye
  2. De-chuan Zhan
  3. Bernt Schiele
  4. Da-Wei Zhou
  5. Qianru Sun
  6. Yaoyao Liu
  7. Guosheng Lin
  8. Wei-Lun Chao

In Computer Vision and Pattern Recognition

  1. Bernt Schiele
  2. Luc Van Gool
  3. Dacheng Tao
  4. Xiaogang Wang
  5. Trevor Darrell
  6. Chunhua Shen
  7. Yi Yang
  8. Ming-Hsuan Yang

In Meta & Continual Learning

  1. Han-Jia Ye
  2. De-chuan Zhan
  3. Da-Wei Zhou
  4. Bernt Schiele
  5. Yaoyao Liu
  6. Qianru Sun
  7. Wei-Lun Chao
  8. Chi Zhang

Citations in the corpus