Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning

About

In this work, we develop methods for few-shot image classification from a new perspective of optimal matching between image regions. We employ 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 calculate 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 alleviate the adverse impact caused by the cluttered background and large intra-class appearance variations. To implement 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. Our extensive experiments validate the effectiveness of our algorithm which outperforms state-of-the-art methods by a significant margin on five widely used few-shot classification benchmarks, namely, miniImageNet, tieredImageNet, Fewshot-CIFAR100 (FC100), Caltech-UCSD Birds-200-2011 (CUB), and CIFAR-FewShot (CIFAR-FS). We also demonstrate the effectiveness of our method on the image retrieval task in our experiments.

Chi Zhang, Yujun Cai, Guosheng Lin, Chunhua Shen• 2020

Related benchmarks

TaskDatasetResultRank
Few-Shot Class-Incremental LearningminiImageNet (test)
Accuracy (Session 1)64.59
173
Few-shot Image ClassificationminiImageNet (test)--
111
Few-shot classificationCUB
Accuracy91.6
96
Few-Shot Class-Incremental LearningCUB200 (incremental sessions)
Session 0 Accuracy75.35
37
Few-shot classificationmeta-iNat fine-grained
Accuracy86.82
36
Few-shot classificationtiered-meta-iNat fine-grained
Accuracy66.27
36
Showing 6 of 6 rows

Other info

Follow for update