paper-with-me

홈 › Papers

Categorical Mixture Models on VGGNet activations

2018-03-06 · Sean Billings

In this project, I use unsupervised learning techniques in order to cluster a set of yelp restaurant photos under meaningful topics. In order to do this, I extract layer activations from a pre-trained implementation of the popular VGGNet convolutional neural network. First, I explore using LDA with the activations of convolutional layers as features. Secondly, I explore using the object-recognition powers of VGGNet trained on ImageNet in order to extract meaningful objects from the photos, and then perform LDA to group the photos under topic-archetypes. I find that this second approach finds meaningful archetypes, which match the human intuition for photo topics such as restaurant, food, and drinks. Furthermore, these clusters align well and distinctly with the actual yelp photo labels.

📄 PDF Abstract BibTeX arXiv:1803.02446

Code (0)

등록된 구현이 없습니다.

Tasks

Object Recognition

Methods 이 논문이 사용한 방법론

LDA Linear discriminant analysis (LDA), normal discriminant analysis (NDA), or discriminant function analysis is a generalization of Fisher's linear discriminant, a method used in…

Similar Papers 제목 키워드 기반

Places205-VGGNet Models for Scene Recognition

2015-08-07 · Limin Wang, Sheng Guo, Weilin Huang, Yu Qiao

VGGNets have turned out to be effective for object recognition in still images. However, it is unable to yield good performance by directly adapting the VGGNet models trained on the ImageNet dataset for scene recognition…

Computational EfficiencyGPUObject RecognitionScene Recognition

CateNorm: Categorical Normalization for Robust Medical Image Segmentation

2021-03-29 · Junfei Xiao, Lequan Yu, Zongwei Zhou, Yutong Bai 외

Batch normalization (BN) uniformly shifts and scales the activations based on the statistics of a batch of images. However, the intensity distribution of the background pixels often dominates the BN statistics because th…

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

GDRQ: Group-based Distribution Reshaping for Quantization

2019-08-05 · Haibao Yu, Tuopu Wen, Guangliang Cheng, Jiankai Sun 외

Low-bit quantization is challenging to maintain high performance with limited model capacity (e.g., 4-bit for both weights and activations). Naturally, the distribution of both weights and activations in deep neural netw…

Quantization

GALILEO: A Generalized Low-Entropy Mixture Model

2017-08-24 · Cetin Savkli, Jeffrey Lin, Philip Graff, Matthew Kinsey

We present a new method of generating mixture models for data with categorical attributes. The keys to this approach are an entropy-based density metric in categorical space and annealing of high-entropy/low-density comp…

Clusteringmodel

A Mean Field Games model for finite mixtures of Bernoulli and Categorical distributions

2020-04-17 · Laura Aquilanti, Simone Cacace, Fabio Camilli, Raul De Maio

Finite mixture models are an important tool in the statistical analysis of data, for example in data clustering. The optimal parameters of a mixture model are usually computed by maximizing the log-likelihood functional …

Clustering