Confidence-Rated Multiple Instance Boosting for Object Detection

By Karim Ali, Kate Saenko. 2014

39 citations recorded by the source corpus.

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Fully Convolutional Multi-Class Multiple Instance Learning (2014, methodology): “Most MIL problems are framed as max-margin learning (Andrews et al., 2002; Felzenszwalb et al., 2010), while other approaches use boosting (Ali & Saenko, 2014) or Noisy-OR models (Heckerman, 2013).”
LSDA: Large Scale Detection through Adaptation (2014, background): “[6] constructs positive bags from all object proposal regions in a weakly labeled image that is known to contain the object, and uses a version of MIL to learn an object detector.”
Self-taught object localization with deep networks (2014, methodology): “A multiple instance learning framework was proposed in [8, 3], and similarly in [27] using latent SVMs, where the latent variable is the location of the object.”
Detector discovery in the wild: Joint multiple instance and representation learning (2014, background): “Multiple Instance Learning Since its inception, the MIL [11] problem has been attempted in several frameworks including Noisy-OR [18], boosting [2, 40] etc.”
Cross-modal adaptation for RGB-D detection (2016, background): “In addition, all variants of our algorithm as well as all baseline and state-of-the-art results are reported using the AlexNet architecture, pre-trained with ImageNet RGB classification data.”
Multiple instance learning: A survey of problem characteristics and applications (2016, methodology): “Other methods, like CR-MILBoost [66] and RSIS [30], estimate the probability that each instance is positive before training an ensemble of classifiers.”