Kernel Relative-prototype Spectral Filtering for Few-shot Learning
- URL: http://arxiv.org/abs/2207.11685v1
- Date: Sun, 24 Jul 2022 07:53:27 GMT
- Title: Kernel Relative-prototype Spectral Filtering for Few-shot Learning
- Authors: Tao Zhang, Wu Huang
- Abstract summary: Few-shot learning performs classification tasks and regression tasks on scarce samples.
In this paper, we propose a framework of spectral filtering (shrinkage) for measuring the difference between query samples and prototypes.
- Score: 3.2091741098687696
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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 prototype,
and measures the similarity of samples and prototypes by Euclidean distance. In
this paper, we propose a framework of spectral filtering (shrinkage) for
measuring the difference between query samples and prototypes, or namely the
relative prototypes, in a reproducing kernel Hilbert space (RKHS). In this
framework, we further propose a method utilizing Tikhonov regularization as the
filter function for few-shot classification. We conduct several experiments to
verify our method utilizing different kernels based on the miniImageNet
dataset, tiered-ImageNet dataset and CIFAR-FS dataset. The experimental results
show that the proposed model can perform the state-of-the-art. In addition, the
experimental results show that the proposed shrinkage method can boost the
performance. Source code is available at https://github.com/zhangtao2022/DSFN.
Related papers
- Hierarchical Visual Categories Modeling: A Joint Representation Learning and Density Estimation Framework for Out-of-Distribution Detection [28.442470704073767]
This paper proposes a novel hierarchical visual category modeling scheme to separate out-of-distribution data from in-distribution data.
We conduct experiments on seven popular benchmarks, including CIFAR, iNaturalist, SUN, Places, Textures, ImageNet-O, and OpenImage-O.
Our visual representation has a competitive performance when compared with features learned by classical methods.
arXiv Detail & Related papers (2024-08-28T07:05:46Z) - Convolutional autoencoder-based multimodal one-class classification [80.52334952912808]
One-class classification refers to approaches of learning using data from a single class only.
We propose a deep learning one-class classification method suitable for multimodal data.
arXiv Detail & Related papers (2023-09-25T12:31:18Z) - SENet: A Spectral Filtering Approach to Represent Exemplars for Few-shot
Learning [5.601374466082551]
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.
A shrinkage exemplar loss is proposed to replace the widely used cross entropy loss for capturing the information of individual shrinkage samples.
arXiv Detail & Related papers (2023-05-30T12:12:39Z) - Revisiting the Evaluation of Image Synthesis with GANs [55.72247435112475]
This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models.
In particular, we make in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set.
arXiv Detail & Related papers (2023-04-04T17:54:32Z) - Which Pixel to Annotate: a Label-Efficient Nuclei Segmentation Framework [70.18084425770091]
Deep neural networks have been widely applied in nuclei instance segmentation of H&E stained pathology images.
It is inefficient and unnecessary to label all pixels for a dataset of nuclei images which usually contain similar and redundant patterns.
We propose a novel full nuclei segmentation framework that chooses only a few image patches to be annotated, augments the training set from the selected samples, and achieves nuclei segmentation in a semi-supervised manner.
arXiv Detail & Related papers (2022-12-20T14:53:26Z) - Generating Representative Samples for Few-Shot Classification [8.62483598990205]
Few-shot learning aims to learn new categories with a few visual samples per class.
Few-shot class representations are often biased due to data scarcity.
We generate visual samples based on semantic embeddings using a conditional variational autoencoder model.
arXiv Detail & Related papers (2022-05-05T20:58:33Z) - Rethinking Semantic Segmentation: A Prototype View [126.59244185849838]
We present a nonparametric semantic segmentation model based on non-learnable prototypes.
Our framework yields compelling results over several datasets.
We expect this work will provoke a rethink of the current de facto semantic segmentation model design.
arXiv Detail & Related papers (2022-03-28T21:15:32Z) - Sampling from Arbitrary Functions via PSD Models [55.41644538483948]
We take a two-step approach by first modeling the probability distribution and then sampling from that model.
We show that these models can approximate a large class of densities concisely using few evaluations, and present a simple algorithm to effectively sample from these models.
arXiv Detail & Related papers (2021-10-20T12:25:22Z) - Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation
for Few-Shot Learning [23.465747123791772]
In few-shot classification, the primary goal is to learn representations that generalize well for novel classes.
We propose an efficient low displacement rank (LDR) regularization strategy termed Ortho-Shot.
arXiv Detail & Related papers (2021-10-18T14:58:36Z) - Multi-Scale Positive Sample Refinement for Few-Shot Object Detection [61.60255654558682]
Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances.
We propose a Multi-scale Positive Sample Refinement (MPSR) approach to enrich object scales in FSOD.
MPSR generates multi-scale positive samples as object pyramids and refines the prediction at various scales.
arXiv Detail & Related papers (2020-07-18T09:48:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.