Abstract
In this paper, we study the problem of fine-grained image categorization. The goal of our method is to explore fine image statistics and identify the discriminative image patches for recognition. We achieve this goal by combining two ideas, discriminative feature mining and randomization. Discriminative feature mining allows us to model the detailed information that distinguishes different classes of images, while randomization allows us to handle the huge feature space and prevents over-fitting. We propose a random forest with discriminative decision trees algorithm, where every tree node is a discriminative classifier that is trained by combining the information in this node as well as all upstream nodes. Our method is tested on both subordinate categorization and activity recognition datasets. Experimental results show that our method identifies semantically meaningful visual information and outperforms state-of-the-art algorithms on various datasets.
Keywords
Discriminative modelComputer scienceCategorizationArtificial intelligencePattern recognition (psychology)Random forestClassifier (UML)Decision treeContextual image classificationFeature extractionMachine learningFeature vectorFeature (linguistics)Tree (set theory)VisualizationImage (mathematics)Data miningMathematics
Affiliated Institutions
Related Publications
A Deep Sum-Product Architecture for Robust Facial Attributes Analysis
Recent works have shown that facial attributes are useful in a number of applications such as face recognition and retrieval. However, estimating attributes in images with large...
The random subspace method for constructing decision forests
Much of previous attention on decision trees focuses on the splitting criteria and optimization of tree sizes. The dilemma between overfitting and achieving maximum accuracy is ...
Shape Quantization and Recognition with Randomized Trees
We explore a new approach to shape recognition based on a virtually infinite family of binary features (queries) of the image data, designed to accommodate prior information abo...
A Communication-Efficient Parallel Algorithm for Decision Tree
Decision tree (and its extensions such as Gradient Boosting Decision Trees and Random Forest) is a widely used machine learning algorithm, due to its practical effectiveness and...
Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy
Feature selection is an important problem for pattern classification systems. We study how to select good features according to the maximal statistical dependency criterion base...
Publication Info
- Year
- 2011
- Type
- article
- Pages
- 1577-1584
- Citations
- 293
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
293
OpenAlex
Cite This
Bangpeng Yao,
Aditya Khosla,
Li Fei-Fei
(2011).
Combining randomization and discrimination for fine-grained image categorization.
, 1577-1584.
https://doi.org/10.1109/cvpr.2011.5995368
Identifiers
- DOI
- 10.1109/cvpr.2011.5995368