Invariant Object Recognition with Slow Feature Analysis

By Mathias Franzius, Niko Wilbert, Laurenz Wiskott. 2008

74 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Cognitive Neuroscience, 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 Aerospace Engineering

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Pylearn2: a machine learning research library (2013, background): “…the CIFAR-10 and CIFAR-100 datasets [29], the MNIST dataset [34], some of the MNIST variations datasets [31], the NORB dataset [35], the Street View House Numbers dataset [36], the Toronto Faces Database [50], some of the UCI repository datasets [17, 16], and a dataset of 3D animations of ﬁsh [18].”
A High-Throughput Screening Approach to Discovering Good Forms of Biologically Inspired Visual Representation (2009, neutral): “[4,20–22]).”
Reinforcement Learning on Slow Features of High-Dimensional Input Streams (2010, methodology): “But this information can easily be extracted from the SFA output, see [15].”
Modular Toolkit for Data Processing (MDP): A Python Data Processing Framework (2008, unknown): “…a model of the visual system of a virtual rat moving around in a virtual environment (Franzius et al., 2007), to perform pattern recognition (Franzius et al., 2008) and handwritten digit recognition (Berkes, 2006), to analyze intra-cerebral array-recorded neurophysiological data in the…”
A Structured Model of Video Reproduces Primary Visual Cortical Organisation (2009, background): “In [27,81] it is shown that the representation learnt by the Slow Feature Analysis algorithm preserves the attribute information.”
Unsupervised learning of visual invariance with temporal coherence (2011, methodology): “Much prior work has been devoted to learning invariant featu res sing image sequences [13, 8, 14, 12].”
DL-SFA: Deeply-Learned Slow Feature Analysis for Action Recognition (2014, background): “SFA intends to capture the invariant and slowly-varied features from input signals, and has been successfully applied to the self-organized receptive field of cortical neuron from synthetic image sequences [34], and to robust recognition of whole objects [7].”
Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis (2013, background): “The SFA principle has been introduced as a mean to learn invariant representations from transformation sequences [15, 34].”
Deep Learning of Invariant Features via Simulated Fixations in Video (2012, background): “Applications of SFA to computer vision have had limited success, applied primarily to artificially generated graphics data [21].”
How to solve classification and regression problems on high-dimensional data with a supervised extension of slow feature analysis (2013, methodology): “Tang and Zhong (2007) introduced pairwise constraints-guided feature projection (PCGFP), where two types of constraints are allowed.”
Slow Feature Analysis for Human Action Recognition (2012, background): “Recently, Franzius et al. [4] proposed a hierarchical model to learn invariant object representation based on the temporal slowness principle.”