An incremental structured part model for object recognition

Abstract

In this paper, we describe how to build an incremental structured part model for object recognition. The proposed method explores both global structural information and multiple local features of objects for object model characterization. It use part models to represent structure nodes, which encode the local information of an object. The parts are learned through a segmentation and clustering process, and are used to form the part models in terms of multiple feature fusion and multi-class SVMs. The structured part model is then constructed by correlating different parts through a deformable configuration. Furthermore, we present an incremental learning strategy, which learns a part model by using only a small number of training samples. Annotated images with high entropies are used to update the trained model. The advantage of our method is that it captures the inherent connections of the semantic parts of objects and characterizes the structural * Corresponding author.Email addresses: baixiao.buaa@googlemail.com (Xiao Bai), pengren@upc.edu.cn (Peng Ren), huigang2010@gmail.com (Huigang Zhang), jun.zhou@griffith.edu.au (Jun Zhou) February 10, 2015 relationships between them. The proposed approach is evaluated on two datasets and demonstrates advantages over several state-of-the-art part-based methods in the literature. Preprint submitted to Neurocomputing

Investigating the Benefits of Exploiting Incremental Learners Under Active Learning Scheme

“…One of the most popular areas in IncL is image/video data processing. Typical case scenarios are object detection [8] and recognition [9], image segmentation [10] and classification [11], surveillance [12], visual tracking [13] and prediction [14].…”

Performance Evaluation of Online Machine Learning Models Based on Cyclic Dynamic and Feature-Adaptive Time Series

“…Image processing is also another field in which image and video data are usually collected in a streaming fashion and are thus useful in incremental learning. Common problems in this context range from object recognition [26], [27], image segmentation [28], [29], and image representation [30], [31] to…”

Deep learning for semantic segmentation of airborne laser scanning point clouds

“…In incremental learning, the model knowledge is continuously enlarged by the continually added samples. Incremental learning has been investigated in many computer vision applications like object recognition (Bai et al, 2015), image classification (Ristin et al, 2016) and segmentation (Tasar et al, 2018), visual tracking (Dou et al, 2015) and surveillance (Shin et al, 2018). Some researches involve active selection processes in incremental learning for image related tasks (Brust et al, 2020;Zhou et al, 2017).…”