Unsupervised Learning of Probabilistic Object Models - Printable Version +- Free Academic Seminars And Projects Reports (https://easyreport.in) +-- Forum: Seminars Topics And Discussions (https://easyreport.in/forumdisplay.php?fid=30) +--- Forum: Miscellaneous Seminars Topics (https://easyreport.in/forumdisplay.php?fid=21) +---- Forum: General Seminar Topics (https://easyreport.in/forumdisplay.php?fid=58) +---- Thread: Unsupervised Learning of Probabilistic Object Models (/showthread.php?tid=23133) |
Unsupervised Learning of Probabilistic Object Models - priyababa - 08-16-2017 Unsupervised Learning of Probabilistic Object Models [attachment=16243] INTRODUCTION RECENT work on object classification and recognition has tended to represent objects in terms of spatial configurations of features at a small number of interest points [3], [4], [5], [6], [7], [8]. Such models are computationally efficient, for both learning and inference, and can be very effective for tasks such as classification. But they have two major disadvantages: 1) the sparseness of their representations restricts the set of visual tasks they can perform and 2) these models only exploit a small set of image cues 2 LEARNING BY KNOWLEDGE PROPAGATION We now describe our strategy for learning by knowledge propagation. Suppose that our goal is to learn a generative model to explain some complicated data. It may be too hard to attempt a model that can explain all the data in one attempt. An alternative strategy is to build the model incrementally by first modeling those parts of the data, which are the easiest. This will provide the context making it easier to learn models for the rest of the data. 3 THE IMAGE REPRESENTATION This section describes the different image features that we use: 1) interest points (used in POM-IP), 2) regional features (in POM-mask), and 3) edgelets (in POM-edgelet). The interest point features d1 I of an image I used in POMIP are represented by a set of attributed features d1 I fzig, where zi xi; i;Ai with xi the position of the feature in the image, i is the feature s orientation, and Ai is an appearance vector. The procedures used to detect and represent the feature points were described in [1], [2]. 5 POM-MASK The POM-mask uses regional cues to perform segmentation/ localization. It is trained using knowledge from the POM-IP giving crude estimates for the segmentation (e.g., the bounding box of the IPs). This training enables POMmask to learn a shape prior for each aspect of the object. After training, the POM-mask and POM-IP are coupled Fig. 4. During inference, the POM-IP supplies estimates of pose and aspect to help estimate the POM-mask variables. |