SENet: A Spectral Filtering Approach to Represent Exemplars for Few-shot Learning
Prototype is widely used to represent internal structure of category for few-shot learning, which was proposed as a simple inductive bias to address the issue of overfitting. However, since prototype representation is normally averaged from individual samples, it can appropriately to represent some classes but with underfitting to represent some others that can be batter represented by exemplars. To address this problem, in this work, we propose Shrinkage Exemplar Networks (SENet) for few-shot classification. In SENet, categories are represented by the embedding of samples that shrink towards their mean via spectral filtering. Furthermore, a shrinkage exemplar loss is proposed to replace the widely used cross entropy loss for capturing the information of individual shrinkage samples. Several experiments were conducted on miniImageNet, tiered-ImageNet and CIFAR-FS datasets. The experimental results demonstrate the effectiveness of our proposed method.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationFew-Shot LearningInductive BiasMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Kernel Relative-prototype Spectral Filtering for Few-shot Learning
Few-shot learning performs classification tasks and regression tasks on scarce samples. As one of the most representative few-shot learning models, Prototypical Network represents each class as sample average, or a proto…
Few-Shot LearningEvery Shot Counts: Using Exemplars for Repetition Counting in Videos
Video repetition counting infers the number of repetitions of recurring actions or motion within a video. We propose an exemplar-based approach that discovers visual correspondence of video exemplars across repetitions w…
DecoderExemplar-FreeRepetitive Action CountingHIME: Efficient Headshot Image Super-Resolution with Multiple Exemplars
A promising direction for recovering the lost information in low-resolution headshot images is utilizing a set of high-resolution exemplars from the same identity. Complementary images in the reference set can improve th…
Image Super-ResolutionSuper-ResolutionExternal-Memory Networks for Low-Shot Learning of Targets in Forward-Looking-Sonar Imagery
We propose a memory-based framework for real-time, data-efficient target analysis in forward-looking-sonar (FLS) imagery. Our framework relies on first removing non-discriminative details from the imagery using a small-s…
Few-Shot LearningZero-Shot LearningLiteDenseNet: A Lightweight Network for Hyperspectral Image Classification
Hyperspectral Image (HSI) classification based on deep learning has been an attractive area in recent years. However, as a kind of data-driven algorithm, deep learning method usually requires numerous computational resou…
ClassificationDeep LearningGeneral ClassificationHyperspectral Image Classification+2