paper-with-me

홈 › Papers

Visual Recognition with Deep Nearest Centroids

2022-09-15 · Wenguan Wang, Cheng Han, Tianfei Zhou, Dongfang Liu

We devise deep nearest centroids (DNC), a conceptually elegant yet surprisingly effective network for large-scale visual recognition, by revisiting Nearest Centroids, one of the most classic and simple classifiers. Current deep models learn the classifier in a fully parametric manner, ignoring the latent data structure and lacking simplicity and explainability. DNC instead conducts nonparametric, case-based reasoning; it utilizes sub-centroids of training samples to describe class distributions and clearly explains the classification as the proximity of test data and the class sub-centroids in the feature space. Due to the distance-based nature, the network output dimensionality is flexible, and all the learnable parameters are only for data embedding. That means all the knowledge learnt for ImageNet classification can be completely transferred for pixel recognition learning, under the "pre-training and fine-tuning" paradigm. Apart from its nested simplicity and intuitive decision-making mechanism, DNC can even possess ad-hoc explainability when the sub-centroids are selected as actual training images that humans can view and inspect. Compared with parametric counterparts, DNC performs better on image classification (CIFAR-10, ImageNet) and greatly boots pixel recognition (ADE20K, Cityscapes), with improved transparency and fewer learnable parameters, using various network architectures (ResNet, Swin) and segmentation models (FCN, DeepLabV3, Swin). We feel this work brings fundamental insights into related fields.

📄 PDF Abstract BibTeX arXiv:2209.07383

Code (1)

chenghan111/dnc 공식 구현 pytorch

Tasks

Decision Makingimage-classificationImage ClassificationObject Recognition

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Improving the accuracy of nearest-neighbor classification using principled construction and stochastic sampling of training-set centroids

2018-09-07 · Stephen Whitelam

A conceptually simple way to classify images is to directly compare test-set data and training-set data. The accuracy of this approach is limited by the method of comparison used, and by the extent to which the training-…

ClassificationGeneral Classification

Learning from One and Only One Shot

2022-01-14 · Haizi Yu, Igor Mineyev, Lav R. Varshney, James A. Evans

Humans can generalize from only a few examples and from little pretraining on similar tasks. Yet, machine learning (ML) typically requires large data to learn or pre-learn to transfer. Motivated by nativism and artificia…

Few-Shot Learning

Classification with Nearest Disjoint Centroids

2021-09-21 · Nicolas Fraiman, Zichao Li

In this paper, we develop a new classification method based on nearest centroid, and it is called the nearest disjoint centroid classifier. Our method differs from the nearest centroid classifier in the following two asp…

Classificationfeature selection

Multilayer bootstrap networks

2014-08-05 · Xiao-Lei Zhang

Multilayer bootstrap network builds a gradually narrowed multilayer nonlinear network from bottom up for unsupervised nonlinear dimensionality reduction. Each layer of the network is a nonparametric density estimator. It…

ClusteringDimensionality Reduction

Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain Adaptation

2019-06-01 · CVPR 2019 6 · Jian Liang, Ran He, Zhenan Sun, Tieniu Tan

Conventional domain adaptation methods usually resort to deep neural networks or subspace learning to find invariant representations across domains. However, most deep learning methods highly rely on large-size source d…

Domain AdaptationDomain GeneralizationFace RecognitionPrivacy Preserving