Scene Classification Using a Hybrid Generative/Discriminative Approach

By Anna Bosch, Andrew Zisserman, Xavier Muñoz. 2008

798 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Latent Dirichlet Allocation Models for Image Classification (2013, methodology): “One popular extension is to apply a classifier, such as an SVM, to the topic representation [4], [5], [18].”
Generative-Discriminative Basis Learning for Medical Imaging (2012, background): “In other words, values of voxels or Regions of Interest (ROI’s) showing significant group difference are not necessarily good discriminatory factors at the patient-level.”
SIFT and color feature fusion using localized maximum-margin learning for scene classification (2011, methodology): “The performance of the proposed scene classification method is tested on an outdoor scene dataset which has been widely used in previous research [14, 22-24].”
Land-Use Scene Classification in High-Resolution Remote Sensing Images Using Improved Correlatons (2015, methodology): “Recently, the Bag-of-Visual-Words (BoVW) model initially proposed for text categorization has been successfully applied to image classification [4]–[6], natural scene categorization [7]–[9], and land-use scene classification using HRIs [10], [11].”
Feature representation for statistical-learning-based object detection: A review (2015, methodology): “HSV-SIFT [71] is the concatenation of dense SIFT descriptors [2] in the HSV color channels.”
From BoW to CNN: Two Decades of Texture Representation for Texture Classification (2018, background): “The importance of texture representations (such as Gabor filters [148], LBP [163], BoT [114], Fisher Vector (FV) [203], and wavelet Scattering Convolution Networks (ScatNet) [24]) is that they were found to be well applicable to other problems of image understanding and computer vision, such as obje”
CENTRIST: A Visual Descriptor for Scene Categorization (2011, methodology): “Scene recognition, or scene categorization, is a term that is usually used to refer to the problem of recognizing the semantic label (e.g., bedroom, mountain, or coast) of a single image [7], [8], [9], [10], [11].”
SIFT Meets CNN: A Decade Survey of Instance Retrieval (2016, methodology): “Evaluation has been conducted on several recognition benchmarks [93] of the descriptors such as HSV-SIFT [94], HueSIFT [95] and OpponentSIFT [93].”
Linear spatial pyramid matching using sparse coding for image classification (2009, background): “Over the years many works have been done to improve the traditional BoF model, such as generative methods in [7, 21, 3, 1] for modeling the co-occurrence of the codewords or descriptors, discriminative codebook learning in [10, 5, 19, 27] instead of standard unsupervised K-means clustering, and spat”
Bag-of-Visual-Words Scene Classifier With Local and Global Features for High Spatial Resolution Remote Sensing Imagery (2016, neutral): “[19], respectively, are also shown for comparison.”
Unsupervised Quaternion Feature Learning for Remote Sensing Image Classification (2016, background): “, [20], raw image patches were shown to yield inferior image representations to SIFT descriptors with regard to classification accuracy.”