Learning From a Small Number of Training Examples by Exploiting Object Categories (original) (raw)

A supervised learning framework for generic object detection in images

Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2005

In recent years Kernel Principal Component Analysis (Kernel PCA) has gained much attention because of its ability to capture nonlinear image features, which are particularly important for encoding image structure. Boosting has been established as a powerful learning algorithm that can be used for feature selection. In this paper we present a novel framework for object class detection that combines the feature reduction and feature selection abilities of Kernel PCA and AdaBoost respectively. The classifier obtained in this way is able to handle change in object appearance, illumination conditions, and surrounding clutter. A nonlinear subspace is learned for positive and negative object classes using Kernel PCA. Features are derived by projecting example images onto the learned subspaces. Base learners are modeled using Bayes classifier. AdaBoost is then employed to discover the features that are most relevant for the object detection task at hand. The proposed method has been successfully tested on wide range of object classes (cars, airplanes, pedestrians, motorcycles, etc) using standard data sets and has shown remarkable performance. Using a small training set, a classifier learned in this way was able to generalize the intra-class variation while still maintaining high detection rate. In most object categories we achieved detection rates of above 95% with minimal false alarm rates. We demonstrate the effectiveness of our approach in terms of absolute performance parameters and comparative performance against current state of the art approaches.

Fast and Robust Object Detection Using Visual Subcategories

2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2014

Object classes generally contain large intra-class variation, which poses a challenge to object detection schemes. In this work, we study visual subcategorization as a means of capturing appearance variation. First, training data is clustered using color and gradient features. Second, the clustering is used to learn an ensemble of models that capture visual variation due to varying orientation, truncation, and occlusion degree. Fast object detection is achieved with integral image features and pixel lookup features. The framework is studied in the context of vehicle detection on the challenging KITTI dataset.

Learning to Detect Objects of Many Classes Using Binary Classifiers

Viola and Jones [VJ] demonstrate that cascade classification methods can successfully detect objects belonging to a single class, such as faces. Detecting and identifying objects that belong to any of a set of "classes", many class detection, is a much more challenging problem. We show that objects from each class can form a "cluster" in a "classifier space" and illustrate examples of such clusters using images of real world objects. Our detection algorithm uses a "decision tree classifier" (whose internal nodes each correspond to a VJ classifier) to propose a class label for every sub-image W of a test image (or reject it as a negative instance). If this W reaches a leaf of this tree, we then pass W through a subsequent VJ cascade of classifiers, specific to the identified class, to determine whether W is truly an instance of the proposed class. We perform several empirical studies to compare our system for detecting objects of any of M classes, to the obvious approach of running a set of M learned VJ cascade classifiers, one for each class of objects, on the same image. We found that the detection rates are comparable, and our many-class detection system is about as fast as running a single VJ cascade, and scales up well as the number of classes increases.

Robust Object Detection using Fast Feature Selection from Huge Feature Sets

2006 International Conference on Image Processing, 2006

This paper describes an efficient feature selection method that quickly selects a small subset out of a given huge feature set; for building robust object detection systems. In this filterbased method, features are selected not only to maximize their relevance with the target class but also to minimize their mutual dependency. As a result, the selected feature set contains only highly informative and non-redundant features, which significantly improve classification performance when combined. The relevance and mutual dependency of features are measured by using conditional mutual information (CMI) in which features and classes are treated as discrete random variables. Experiments on different huge feature sets have shown that the proposed CMI-based feature selection can both reduce the training time significantly and achieve high accuracy.

Joint feature selection for object detection and recognition

2006

Object detection and recognition systems, such as face detectors and face recognizers, are often trained separately and operated in a feed-forward fashion. Selecting a small number of features for these tasks is important to prevent over-fitting and reduce computation. However, when a system has such related or sequential tasks, selecting features for these tasks independently may not be optimal. We propose a framework for choosing features to be shared between object detection and recognition tasks. The result is a system that achieves better performance by joint training and is faster because some features for identification have already been computed for detection. We demonstrate with experiments in text detection and character recognition for images of scenes.

Towards automatic discovery of object categories

2000

Abstract We propose a method to learn heterogeneous models of object classes for visual recognition. The training images contain a preponderance of clutter and learning is unsupervised. Our models represent objects as probabilistic constellations of rigid parts (features). The variability within a class is represented by a join probability density function on the shape of the constellation and the appearance of the parts. Our method automatically identifies distinctive features in the training set.

An Efficient Feature Selection Method for Object Detection

Lecture Notes in Computer Science, 2005

We propose a simple yet efficient feature-selection method -based on principle component analysis (PCA) -for SVM-based classifiers. The idea is to select features whose corresponding axes are closest to the principle components computed from a data distribution by PCA. Experimental results show that our proposed method reduces dimensionality similar to PCA, but maintains the original measurement meanings while decreasing the computation time significantly.

An Active Search Strategy for Efficient Object Class Detection

2015

Object class detectors typically apply a window classifier to all the windows in a large set, either in a sliding window manner or using object proposals. In this paper, we develop an active search strategy that sequentially chooses the next window to evaluate based on all the information gathered before. This results in a substantial reduction in the number of classifier evaluations and in a more elegant approach in general. Our search strategy is guided by two forces. First, we exploit context as the statistical relation between the appearance of a window and its location relative to the object, as observed in the training set. This enables to jump across distant regions in the image (e.g. observing a sky region suggests that cars might be far below) and is done efficiently in a Random Forest framework. Second, we exploit the score of the classifier to attract the search to promising areas surrounding a highly scored window, and to keep away from areas near low scored ones. Our search strategy can be applied on top of any classifier as it treats it as a black-box. In experiments with R-CNN on the challenging SUN2012 dataset, our method matches the detection accuracy of evaluating all windows independently, while evaluating 9× fewer windows.

RelCom: Relational combinatorics features for rapid object detection

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, 2010

We present a simple yet elegant feature, RelCom, and a boosted selection method to achieve a very low complexity object detector. We generate combinations of low-level feature coefficients and apply relational operations such as margin based similarity rule over each possible pair of these combinations to construct a proposition space. From this space we define combinatorial functions of Boolean operators to form complex hypotheses that model any logical proposition. In case these coefficients are associated with the pixel coordinates, they encapsulate higher order spatial structure within the object window. Our results on benchmark datasets prove that the boosted RelCom features can match the performance of HOG features of SVM-RBF while providing 5X speed up and significantly outperform SVM-linear while reducing the false alarm rate 5X 20X. In case of intensity features the improvement in false alarm rate over SVM-RBF is 14X with a 128X speed up. We also demonstrate that RelCom based on pixel features is very suitable and efficient for small object detection tasks.