'Breaking' position-invariant object recognition

By David D. Cox, Philip Meier, Nadja Oertelt, James J. DiCarlo. 2005

178 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, 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 Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation (2016, positive): “There is considerable evidence from physiology and psychophysics that the brain employs a temporal-association strategy of this sort [35, 56, 12, 30, 57, 31].”
How does the brain solve visual object recognition? (2012, positive): “Indeed, artificial manipulations of temporally contiguous experience with object images across different positions and sizes can rapidly and strongly reshape the position and size tolerance of IT neurons -- destroying existing tolerance and building new tolerance, depending on the provided visual ex”
A High-Throughput Screening Approach to Discovering Good Forms of Biologically Inspired Visual Representation (2009, positive): “Building upon recent findings from visual neuroscience [18,23,24], unsupervised learning could also be biased by temporal factors, such that filters that ‘‘won’’ in previous frames were biased to win again (see Supplemental Text S1 for details).”
Unsupervised Learning of Invariant Representations in Hierarchical Architectures (2013, methodology): “If the sparsity condition holds only for I = t and for very small set of g ∈ G, that is, it has the form 〈 I, gt 〉 = δ(g)δI,tk it implies strict memory-based recognition ( see non-interpolating look-up table in the description of [10]) with inability to generalize beyond stored templates or views.”
Unsupervised Natural Visual Experience Rapidly Reshapes Size Invariant Object Representation in Inferior Temporal Cortex (2010, unknown): “This IT neuronal learning likely has perceptual consequences because similar temporal contiguity manipulations of eye-movementdriven position experience can produce qualitatively similar changes in the position tolerance of human object perception (Cox et al., 2005).”
Learning Invariance from Natural Images Inspired by Observations in the Primary Visual Cortex (2012, background): “Such properties are not rigidly encoded in the visual system; they are a product of learning and adaption in the visual system (Cox, Meier, Oertelt, & DiCarlo, 2005; Li & DiCarlo, 2010).”
Learning illumination- and orientation-invariant representations of objects through temporal association. (2009, background): “One reason for thinking this is that although the original description of temporal association-based learning concerned faces (Wallis & Bu¨lthoff, 2001), similar effects have since been reported for a range of novel object classes both in humans (Liu, 2007; Vuong & Tarr, 2004), and monkeys ( Cox, Me”
Opposite modulation of high- and low-level visual aftereffects by perceptual grouping (2012, unknown): “A dominant functional interpretation of the feedforward ventral pathway is increased selectivity at the expense of insensitivity to variables such as translation, illumination, and scale; but if information about position and size is gradually lost, then how could a feedback signal be spatially prec”
Deep Learning of Invariant Features via Simulated Fixations in Video (2012, background): “Experimental evidence suggests that high-level visual representations become slow-changing and tolerant towards non-trivial transformations, by associating low-level features which appear in a coherent sequence [5].”
How the brain might work: a hierarchical and temporal model for learning and recognition (2008, background): “The above discussion can be distilled into two main points: (1)A recent experiment by Cox, Meier, Oertelt and DiCarlo lab showed that position invariant object recognition can be broken by changing the temporal statistics of presentation of the objects [18].”
Unsupervised learning of visual invariance with temporal coherence (2011, methodology): “The learned features out-perform features learned with sparsity in vision benchmarks Caltech-101, STL-10 and COIL-100.”