159 papers with code • 17 benchmarks • 14 datasets
Object Localization is the task of locating an instance of a particular object category in an image, typically by specifying a tightly cropped bounding box centered on the instance. An object proposal specifies a candidate bounding box, and an object proposal is said to be a correct localization if it sufficiently overlaps a human-labeled “ground-truth” bounding box for the given object. In the literature, the “Object Localization” task is to locate one instance of an object category, whereas “object detection” focuses on locating all instances of a category in a given image.
Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality.
In this work, we revisit the global average pooling layer proposed in , and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels.
Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers.
Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems.
Bridging the 'reality gap' that separates simulated robotics from experiments on hardware could accelerate robotic research through improved data availability.
The Earth ain't Flat: Monocular Reconstruction of Vehicles on Steep and Graded Roads from a Moving Camera
The proposed approach significantly improves the state-of-the-art for monocular object localization on arbitrarily-shaped roads.