Self-Adaptable Templates for Feature Coding
نویسندگان
چکیده
Hierarchical feed-forward networks have been successfully applied in object recognition. At each level of the hierarchy, features are extracted and encoded, followed by a pooling step. Within this processing pipeline, the common trend is to learn the feature coding templates, often referred as codebook entries, filters, or over-complete basis. Recently, an approach that apparently does not use templates has been shown to obtain very promising results. This is the second-order pooling (O2P) [1, 2, 3, 4, 5]. In this paper, we analyze O2P as a coding-pooling scheme. We find that at testing phase, O2P automatically adapts the feature coding templates to the input features, rather than using templates learned during the training phase. From this finding, we are able to bring common concepts of coding-pooling schemes to O2P, such as feature quantization. This allows for significant accuracy improvements of O2P in standard benchmarks of image classification, namely Caltech101 and VOC07.
منابع مشابه
Classification of Bioacoustic Time Series by Training a Fusion Layer with Decision Templates
The classification of time series is the topic of this paper. In particular we discuss the combination of local classifier decisions from several feature spaces with static and adaptable fusion schemes, e.g. averaging and decision templates. The decision templates are calculated over a set of feature vectors which are extracted in local time windows. We present algorithms to calculate decision ...
متن کاملNose shape estimation and tracking for model-based coding
Feature extraction on the face plays an important role in applications of model based coding and human face recognition. Traditionally, eyes and mouth are considered to be the most significant features contributing to different facial expressions. However, detecting and tracking the nose shape is non-trivial, and plays an equally important role as eyes and mouth for model based coding, especial...
متن کاملMultimodal Sparse Features for Object Detection
In this paper the sparse coding principle is employed for the representation of multimodal image data, i.e. image intensity and range. We estimate an image basis for frontal face images taken with a Time-ofFlight (TOF) camera to obtain a sparse representation of facial features, such as the nose. These features are then evaluated in an object detection scenario where we estimate the position of...
متن کامل3D Model-Based Head Tracking
This paper introduces a new approach to feature-based head tracking and pose estimation. Head tracking and pose estimation nd their most important applications in motion analysis for model-based video coding. The proposed algorithm employs an underlying 3D head model, feature-based pose estimation, and texture mapping to produce accurate templates for the feature tracking. In this way, the set ...
متن کاملA Rendezvous of Content Adaptable Service and Product Line Modeling
Content adaptable applications are often used in ubiquitous computing environment, and it aims to service the adaptable contents to users. In this environment, the services are dynamically selected and provided, the contexts are changed frequently. Then, the application services are to be modeled to derive the adaptable service effectively and to reuse the model. Modeling with software features...
متن کامل