A Coarse-to-Fine Taxonomy of Constellations for Fast Multi-class Object Detection
نویسندگان
چکیده
In order for recognition systems to scale to a larger number of object categories building visual class taxonomies is important to achieve running times logarithmic in the number of classes [1, 2]. In this paper we propose a novel approach for speeding up recognition times of multi-class part-based object representations. The main idea is to construct a taxonomy of constellation models cascaded from coarse-to-fine resolution and use it in recognition with an efficient search strategy. The taxonomy is built automatically in a way to minimize the number of expected computations during recognition by optimizing the cost-to-power ratio [3]. The structure and the depth of the taxonomy is not pre-determined but is inferred from the data. The approach is utilized on the hierarchy-of-parts model [4] achieving efficiency in both, the representation of the structure of objects as well as in the number of modeled object classes. We achieve speed-up even for a small number of object classes on the ETHZ and TUD dataset. On a larger scale, our approach achieves detection time that is logarithmic in the number of classes.
منابع مشابه
Non-expert Labels Improve Fine-Grained Object Recognition
Fine-grained object recognition typically requires domain experts to provide class label annotations, making these labels difficult to collect when experts are rare. Often, fine-grained classes can be organized into a visual class taxonomy according to shared visual features. In this case, non-experts can easily distinguish between coarse classes, allowing them to annotate examples at a coarse ...
متن کاملObjects Identification in Object-Oriented Software Development - A Taxonomy and Survey on Techniques
Analysis and design of object oriented is onemodern paradigms for developing a system. In this paradigm, there are several objects and each object plays some specific roles. Identifying objects (and classes) is one of the most important steps in the object-oriented paradigm. This paper makes a literature review over techniques to identify objects and then presents six taxonomies for them. The f...
متن کاملTaxonomic Curriculum Learning for Fine-Grained Object Recognition
Drawing inspiration from taxonomic methods of learning and curriculum learning, we propose a new learning method: taxonomic curriculum learning. With this method, given a visual taxonomy of finegrained classes, a classifier is trained in a sequential coarse to fine manner. We compare our method with two baseline methods: the standard approach of purely fine-grained learning and multi-task learn...
متن کاملA Multi-Stage Approach to Fast Face Detection
A multi-stage approach — which is fast, robust and easy to train — for a face-detection system is proposed. Motivated by the work of Viola and Jones [1], this approach uses a cascade of classifiers to yield a coarse-to-fine strategy to reduce significantly detection time while maintaining a high detection rate. However, it is distinguished from previous work by two features. First, a new stage ...
متن کاملObject Detection with Heuristic Coarse-to-Fine Search
We consider the task of localizing and labeling instances of a generic object class within real-world images. Our focus is on a generalized class of pictorial structure models that are defined in terms of visual grammars. In particular, we address the challenging problem of performing detection efficiently even as model complexity grows within this class. Our proposed solution is a blend of heu...
متن کامل