Semi-supervised 3D object recognition through CNN labeling
نویسندگان
چکیده
منابع مشابه
Semi-supervised Semantic Role Labeling
Most corpus-based approaches to language learning have focused on tasks for which a sufficient amount of human-labeled training data is available. However, it is difficult to produce such data, and models trained from such data tend to be brittle when applied to domains that vary, even in seemingly minor ways, from the training data. We claim that these difficulties can by overcome by applying ...
متن کاملSemi-Supervised Semantic Role Labeling
Large scale annotated corpora are prerequisite to developing high-performance semantic role labeling systems. Unfortunately, such corpora are expensive to produce, limited in size, and may not be representative. Our work aims to reduce the annotation effort involved in creating resources for semantic role labeling via semi-supervised learning. Our algorithm augments a small number of manually l...
متن کاملSemi-supervised learning and recognition of object classes
We present a method for learning object classes without supervision: learning is scale and translation-invariant, does not require alignment nor correspondence between the training images, and is robust to clutter and occlusion. Class models are probabilistic constellations of parts, and their parameters are estimated by maximizing the likelihood of the training data. The appearance of the part...
متن کاملSemi-supervised learning for object recognition in RGBz images
In this project I am focused on the problem of using depth information in the absence of labeled depth training data for the task of object detection in RGBz images. This task is important for computers to fully utilize both the breadth of image training data that does not include depth sensors while allowing depth-enabled systems to utilize the valuable added information provided by a depth se...
متن کاملSemi-supervised object recognition based on Connected Image Transformations
We present a novel semi-supervised classifier model based on paths between unlabeled and labeled data through a sequence of local pattern transformations. A reliable measure of path-length is proposed that combines a local dissimilarity measure between consecutive patters along a path with a global, connectivity-based metric. We apply this model to problems of object recognition, for which we p...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Applied Soft Computing
سال: 2018
ISSN: 1568-4946
DOI: 10.1016/j.asoc.2018.02.005