DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover's Distance and Structured Classifiers
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).
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationFew-Shot Image ClassificationGeneral Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning
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…
ClassificationFew-Shot Image ClassificationFew-Shot LearningGeneral Classification+4Differentiable Earth Mover's Distance for Data Compression at the High-Luminosity LHC
The Earth mover's distance (EMD) is a useful metric for image recognition and classification, but its usual implementations are not differentiable or too slow to be used as a loss function for training other algorithms v…
Data CompressionDeepEMD: A Transformer-based Fast Estimation of the Earth Mover's Distance
The Earth Mover's Distance (EMD) is the measure of choice between point clouds. However the computational cost to compute it makes it prohibitive as a training loss, and the standard approach is to use a surrogate such a…
FEDI: Few-shot learning based on Earth Mover's Distance algorithm combined with deep residual network to identify diabetic retinopathy
Diabetic retinopathy(DR) is the main cause of blindness in diabetic patients. However, DR can easily delay the occurrence of blindness through the diagnosis of the fundus. In view of the reality, it is difficult to colle…
Few-Shot LearningDR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction
We introduce a differential visual similarity metric to train deep neural networks for 3D reconstruction, aimed at improving reconstruction quality. The metric compares two 3D shapes by measuring distances between multi-…
3D Reconstruction3D Shape ReconstructionRetrieval