Learning Optimized Features for Hierarchical Models of Invariant Object Recognition

By Heiko Wersing, Edgar Körner. 2003

196 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics, 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 Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Robust Object Recognition with Cortex-Like Mechanisms (2007, background): “While mainstream computer vision has always been inspired and challenged by human vision, it seems to never have advanced past the very first stages of processing in the simple (and binocular) cells in V 1 and V 2. Although some of the systems inspired—to various degrees—by neuroscience [4], [5], [6”
Learning viewpoint invariant object representations using a temporal coherence principle (2005, background): “Wersing and Körner (2003) show that a network trained by the principle of sparse-coding achieves some degree of viewpoint invariance for classifying real-world objects in cluttered scenes.”
Unsupervised learning of visual invariance with temporal coherence (2011, methodology): “In our experiments we followed testing protocols in [28] and use 0, 90, 180, 270 d egree perspectives of objects as supervised training set, and the rest as test set.”
A quantitative theory of immediate visual recognition. (2007, methodology): “A number of biologically inspired algorithms have been described (Fukushima, 1980; LeCun et al., 1998; Ullman et al., 2002; Wersing and Koerner, 2003 ), i.e., systems which are only qualitatively constrained by the anatomy and physiology of the visual cortex.”
Towards a Mathematical Theory of Cortical Micro-circuits (2009, methodology): “The HTM model in this paper uses sparse-distributed representations [68,69] when considering the representations within an entire hierarchical level.”
50 Years of object recognition: Directions forward (2013, methodology): “A hierarchical object recognition architecture, inspired by human vision, is used [218].”
Deep learning from temporal coherence in video (2009, methodology): “Both 30 and 100 objects were used following (Wersing & K¨orner, 2003).”
How the brain might work: a hierarchical and temporal model for learning and recognition (2008, background): “Many computational neuroscientists now believe that the neocortex uses sparsedistributed representations to encode information [87, 107, 106].”