Adaptive Scene Category Discovery with Generative Learning and Compositional Sampling

02/02/2015
by   Liang Lin, et al.
0

This paper investigates a general framework to discover categories of unlabeled scene images according to their appearances (i.e., textures and structures). We jointly solve the two coupled tasks in an unsupervised manner: (i) classifying images without pre-determining the number of categories, and (ii) pursuing generative model for each category. In our method, each image is represented by two types of image descriptors that are effective to capture image appearances from different aspects. By treating each image as a graph vertex, we build up an graph, and pose the image categorization as a graph partition process. Specifically, a partitioned sub-graph can be regarded as a category of scenes, and we define the probabilistic model of graph partition by accumulating the generative models of all separated categories. For efficient inference with the graph, we employ a stochastic cluster sampling algorithm, which is designed based on the Metropolis-Hasting mechanism. During the iterations of inference, the model of each category is analytically updated by a generative learning algorithm. In the experiments, our approach is validated on several challenging databases, and it outperforms other popular state-of-the-art methods. The implementation details and empirical analysis are presented as well.

READ FULL TEXT

page 2

page 3

page 8

page 10

page 11

research
05/27/2022

CIGMO: Categorical invariant representations in a deep generative framework

Data of general object images have two most common structures: (1) each ...
research
05/09/2022

A Probabilistic Generative Model of Free Categories

Applied category theory has recently developed libraries for computing w...
research
04/27/2023

Incremental Generalized Category Discovery

We explore the problem of Incremental Generalized Category Discovery (IG...
research
10/16/2015

No Spare Parts: Sharing Part Detectors for Image Categorization

This work aims for image categorization using a representation of distin...
research
02/07/2023

Structured Generative Models for Scene Understanding

This position paper argues for the use of structured generative models (...
research
06/20/2017

A Bayesian algorithm for detecting identity matches and fraud in image databases

A statistical algorithm for categorizing different types of matches and ...

Please sign up or login with your details

Forgot password? Click here to reset