PennSyn2Real: Training Object Recognition Models Without Human Labeling
نویسندگان
چکیده
Scalable training data generation is a critical problem in deep learning. We propose PennSyn2Real - photo-realistic synthetic dataset consisting of more than 100 000 4K images 20 types micro aerial vehicles (MAVs). The can be used to generate arbitrary numbers for high-level computer vision tasks such as MAV detection and classification. Our framework bootstraps chroma-keying, mature cinematography technique, with motion tracking system providing artifact-free curated annotated images. system, therefore, allows object orientations lighting controlled. This easy set up applied broad range objects, reducing the gap between real-world data. show that generated using this directly train CNN models common recognition segmentation. demonstrate competitive performance comparison only real Furthermore, bootstrapping few-shot learning significantly improve overall performance, number required samples achieve desired accuracy.
منابع مشابه
Learning Models for Object Recognition
We consider learning models for object recognition from examples. Our method is motivated by systems that use the Hausdorff distance as a shape comparison measure. Typically an object is represented in terms of a model shape. A new shape is classified as being an instance of the object when the Hausdorff distance between the model and the new shape is small. We show that such object concepts ca...
متن کاملObject Recognition with 3D Models
Intro: We propose several new ideas of how to use 3D models for viewbased object recognition. In an initial experiment we show that even the simple task of distinguishing between two objects requires large training sets if high accuracy and pose invariance are to be achieved. Using synthetic image data, we propose a method for quantifying the degree of difficulty of detecting objects across vie...
متن کاملIndexing without Invariants in 3D Object Recognition
ÐWe present a method of indexing three-dimensional objects from single two-dimensional images. Unlike most other methods to solve this problem, ours does not rely on invariant features. This allows a richer set of shape information to be used in the recognition process. We also suggest the kd-tree as an alternative indexing data structure to the standard hash table. This makes hypothesis recove...
متن کاملObject Recognition with and without Objects
While recent deep neural network models have given promising performance on object recognition, they rely implicitly on the visual contents of the whole image. In this paper, we train deep neural networks on the foreground (object) and background (context) regions of images respectively. Considering human recognition in the same situations, networks trained on pure background without objects ac...
متن کاملTraining Facilitates Object Recognition in Cubist Paintings
To the naïve observer, cubist paintings contain geometrical forms in which familiar objects are hardly recognizable, even in the presence of a meaningful title. We used fMRI to test whether a short training session about Cubism would facilitate object recognition in paintings by Picasso, Braque and Gris. Subjects, who had no formal art education, were presented with titled or untitled cubist pa...
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: IEEE robotics and automation letters
سال: 2021
ISSN: ['2377-3766']
DOI: https://doi.org/10.1109/lra.2021.3070249