Learning Hybrid Image Templates (HIT) by Information Projection

Abstract

Abstract-This paper presents a novel framework for learning a generative image representation -the hybrid image template (HIT) from a small number (i.e, 3 ∼ 20) of image examples. Each learned template is composed of, typically, 50 ∼ 500 image patches whose geometric attributes (location, scale, orientation) may adapt in a local neighborhood for deformation, and whose appearances are characterized respectively by four types of descriptors: local sketch (edge or bar), texture gradients with orientations, flatness regions, and colors. These heterogeneous patches are automatically ranked and selected from a large pool according to their information gains using an information projection framework. Intuitively, a patch has a higher information gain if (i) its feature statistics is consistent within the training examples and is distinctive from the statistics of negative examples (i.e. generic images or examples from other categories); and (ii) its feature statistics has less intra-class variations. The learning process pursues the most informative (for either generative or discriminative purpose) patches one at a time and stops when the information gain is within statistical fluctuation. The template is associated with a well-normalized probability model that integrates the heterogeneous feature statistics. This automated feature selection procedure allows our algorithm to scale up to a wide range of image categories, from those with regular shapes to those with stochastic texture. The learned representation captures the intrinsic characteristics of the object or scene categories. We evaluate the hybrid image templates on several public benchmarks, and demonstrate classification performances on par with state-of-art methods like HoG+SVM, and when small training sample sizes are used the proposed system shows a clear advantage.

Learning Sparse FRAME Models for Natural Image Patterns

“…Experiment 8: Multi-class classification. Our second set of experiments is on the LHI-Animal-Faces dataset [51], which consists of around 2200 images for 20 categories of animal or human faces. We randomly select half of the images per class for training and the rest for testing.…”

“…Our classification rate is 79.4%. For comparison, Table 3 lists four published results [51] on this dataset obtained by other methods: (a) HoG feature trained with SVM, (b) Hybrid Image Template (HIT) [51], (c) multiple transformation invariant HITs (Mixture of HIT) [51], and (d) part-based HoG feature trained with latent SVM [16]. Our method outperforms the other methods in terms of classification accuracy on this dataset.…”

A Simple Stochastic Algorithm for Structural Features Learning

“…Second experiment had a different scenario, it was done on a single category set of real images of cat faces from the LHI-Animal-Faces dataset [17]. The subset of cat faces consisted of 89 images roughly on a same scale.A small selection of images from this set is shown in the Figure 5(a).The images were preprocessed before entering the learning algorithm in order to extract oriented edge segments.…”

A Pose based Object Recognition Model for Improving Learning Time and Accuracy

“…The AOT includes: 1) hierarchical composition as "AND" nodes, 2) deformation and articulation of parts as geometric "OR" nodes, and 3) multiple ways of composition as structural "OR" nodes. The terminal nodes are hybrid image templates (HIT) [3] that are entirely creative to the pixels. Author shows that both the structures and parameters of the AOT model can be learned in an unsupervised way from images using an information projection principle.…”