Object localization in ImageNet by looking out of the window
By Alexander Vezhnevets, Vittorio Ferrari. 2015
14 citations recorded by the source corpus.
We propose a method for annotating the location of objects in ImageNet. Traditionally, this is cast as an image window classification problem, where each window is considered independently and scored based on its appearance alone. Instead, we propose a method which scores each candidate window in the context of all other windows in the image, taking into account their similarity in appearance space as well as their spatial relations in the image plane. We devise a fast and exact procedure to optimize our scoring function over all candidate windows in an image, and we learn its parameters using structured output regression. We demonstrate on 92000 images from ImageNet that this significantly improves localization over recent techniques that score windows in isolation.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Bernt Schiele
- Rodrigo Benenson
- Jan Hendrik Hosang
- Xiaogang Wang
- Trevor Darrell
- Jitendra Malik
- Terrance E. Boult
- Bharath Hariharan
In Computer Vision and Pattern Recognition
- Bernt Schiele
- Luc Van Gool
- Jitendra Malik
- Xiaogang Wang
- Trevor Darrell
- Andrew Zisserman
- Andrea Vedaldi
- Ming-Hsuan Yang
Citations in the corpus
- Learning Non-maximum Suppression (2017, methodology): “Some methods improve object detection by jointly rescoring detections locally [30, 4] or globally [31] using image information.”
- Towards Open Set Deep Networks (2015, background): “Thus, other uses of the OpenMax rejection can be to improve training process and aid in developing better localization techniques [30, 15].”
- A Convnet for Non-maximum Suppression (2015, methodology): “We adopt from Stewart & Andriluka (2015) the idea of computing the loss by matching detections to annotations, but instead of regressing bounding boxes at every location we predict new detection scores that are high for matched detections and low everywhere else.”
- Exploring Person Context and Local Scene Context for Object Detection (2015, background): “Vezhnevets and Ferrari [30] use all boxes in an image to classify a bounding box.”