Greedy Learning of Multiple Objects in Images Using Robust Statistics and Factorial Learning

By Christopher K. I. Williams, Michalis K. Titsias. 2004

85 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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

In Representation & Self-Supervised Learning

Citations in the corpus

Recurrent Instance Segmentation (2015, background): “Finally, it is worth mentioning the approach in [29] despite not being an RNN, which consists in a greedy sequential algorithm for learning several objects in an image.”
Learning generative models of mid-level structure in natural images (2012, background): “Other models in the computer vision literature can extract information about shape and appearance, illumination, occlusion and other factors of variation in an unsupervised manner (Frey and Jojic, 2003; Williams and Titsias, 2004; Kannan et al., 2005; Winn and Jojic, 2005; Kannan et al., 2007).”
Generative Modeling of Infinite Occluded Objects for Compositional Scene Representation (2019, unknown): “Layered representations have been studied for years in the computer vision community, and several methods which handle occlusions have been proposed (Wang & Adelson, 1994; Williams & Titsias, 2004; Le Roux et al., 2011; Huang & Murphy, 2016; Moreno et al., 2016; Wu et al., 2017).”
A Structured Model of Video Reproduces Primary Visual Cortical Organisation (2009, background): “Our approach is in many ways complementary, in that it starts from the bottom up, and requires no supervision (see [70,78,79] for comparable bottom-up computer vision approaches).”
Efficient inference in occlusion-aware generative models of images (2015, methodology): “Our generative model is similar to that proposed by Williams & Titsias (2004), however we can capture more complex appearance models by using deep neural networks, compared to their per-pixel mixture-of-gaussian models.”
Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views (2021, methodology): “We model an image x t with a spatial Gaussian mixture model[24, 10], similar to MONet[4] and IODINE[9], and additionally we take as input (condition on) the viewpoint v t .”
Robust Boltzmann Machines for recognition and denoising (2012, unknown): “Generative image models with occlusion have been well studied in the vision and machine learning literature [7, 26].”
LOCUS: learning object classes with unsupervised segmentation (2005, background): “This choice of a binary mask (rather than a real valued mask) leads to more efficient and robust inference [14].”