paper-with-me

Papers

Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classification

2020-12-27 · Piotr Koniusz, Hongguang Zhang

Power Normalizations (PN) are useful non-linear operators which tackle feature imbalances in classification problems. We study PNs in the deep learning setup via a novel PN layer pooling feature maps. Our layer combines the feature vectors and their respective spatial locations in the feature maps produced by the last convolutional layer of CNN into a positive definite matrix with second-order statistics to which PN operators are applied, forming so-called Second-order Pooling (SOP). As the main goal of this paper is to study Power Normalizations, we investigate the role and meaning of MaxExp and Gamma, two popular PN functions. To this end, we provide probabilistic interpretations of such element-wise operators and discover surrogates with well-behaved derivatives for end-to-end training. Furthermore, we look at the spectral applicability of MaxExp and Gamma by studying Spectral Power Normalizations (SPN). We show that SPN on the autocorrelation/covariance matrix and the Heat Diffusion Process (HDP) on a graph Laplacian matrix are closely related, thus sharing their properties. Such a finding leads us to the culmination of our work, a fast spectral MaxExp which is a variant of HDP for covariances/autocorrelation matrices. We evaluate our ideas on fine-grained recognition, scene recognition, and material classification, as well as in few-shot learning and graph classification.

📄 PDF Abstract BibTeX arXiv:2012.13975

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot LearningGeneral ClassificationGraph ClassificationMaterial ClassificationScene Recognition

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Power Normalizing Second-order Similarity Network for Few-shot Learning

2018-11-10 · Hongguang Zhang, Piotr Koniusz

Second- and higher-order statistics of data points have played an important role in advancing the state of the art on several computer vision problems such as the fine-grained image and scene recognition. However, these …

Few-Shot LearningScene Recognition

A Deeper Look at Power Normalizations

2018-06-24 · CVPR 2018 6 · Piotr Koniusz, Hongguang Zhang, Fatih Porikli

Power Normalizations (PN) are very useful non-linear operators in the context of Bag-of-Words data representations as they tackle problems such as feature imbalance. In this paper, we reconsider these operators in the de…

Material ClassificationScene Recognition

Efficient Action Localization with Approximately Normalized Fisher Vectors

2014-06-01 · CVPR 2014 6 · Dan Oneata, Jakob Verbeek, Cordelia Schmid

The Fisher vector (FV) representation is a high-dimensional extension of the popular bag-of-word representation. Transformation of the FV by power and L2 normalizations has shown to significantly improve its performance,…

Action LocalizationAction RecognitionGeneral ClassificationRetrieval+3

Dual Attention Networks for Few-Shot Fine-Grained Recognition

2022-06-28 · Proceedings of the AAAI Conference on Artificial Intelligence 2022 6 · Shu-Lin Xu, Faen Zhang, Xiu-Shen Wei, Jianhua Wang

The task of few-shot fine-grained recognition is to classify images belonging to subordinate categories merely depending on few examples. Due to the fine-grained nature, it is desirable to capture subtle but discriminati…

Hard AttentionMeta-Learning

Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition

2019-11-17 · NeurIPS 2019 12 · Satoshi Tsutsui, Yanwei Fu, David Crandall

One-shot fine-grained visual recognition often suffers from the problem of training data scarcity for new fine-grained classes. To alleviate this problem, an off-the-shelf image generator can be applied to synthesize add…

Fine-Grained Image ClassificationFine-Grained Visual Recognitionimage-classificationImage Classification+2