Learning image representations tied to ego-motion
D Jayaraman, K Grauman - Proceedings of the IEEE …, 2015 - openaccess.thecvf.com
Understanding how images of objects and scenes behave in response to specific ego-
motions is a crucial aspect of proper visual development, yet existing visual learning …
motions is a crucial aspect of proper visual development, yet existing visual learning …
Toward a unified theory of efficient, predictive, and sparse coding
A central goal in theoretical neuroscience is to predict the response properties of sensory
neurons from first principles. To this end,“efficient coding” posits that sensory neurons …
neurons from first principles. To this end,“efficient coding” posits that sensory neurons …
[HTML][HTML] Unsupervised learning of mid-level visual representations
Recently, a confluence between trends in neuroscience and machine learning has brought
a renewed focus on unsupervised learning, where sensory processing systems learn to …
a renewed focus on unsupervised learning, where sensory processing systems learn to …
Hierarchical temporal prediction captures motion processing along the visual pathway
Visual neurons respond selectively to features that become increasingly complex from the
eyes to the cortex. Retinal neurons prefer flashing spots of light, primary visual cortical (V1) …
eyes to the cortex. Retinal neurons prefer flashing spots of light, primary visual cortical (V1) …
Unsupervised experience with temporal continuity of the visual environment is causally involved in the development of V1 complex cells
G Matteucci, D Zoccolan - Science advances, 2020 - science.org
Unsupervised adaptation to the spatiotemporal statistics of visual experience is a key
computational principle that has long been assumed to govern postnatal development of …
computational principle that has long been assumed to govern postnatal development of …
A polar prediction model for learning to represent visual transformations
PÉ Fiquet, E Simoncelli - Advances in Neural Information …, 2024 - proceedings.neurips.cc
All organisms make temporal predictions, and their evolutionary fitness level depends on the
accuracy of these predictions. In the context of visual perception, the motions of both the …
accuracy of these predictions. In the context of visual perception, the motions of both the …
Diverse feature visualizations reveal invariances in early layers of deep neural networks
Visualizing features in deep neural networks (DNNs) can help understanding their
computations. Many previous studies aimed to visualize the selectivity of individual units by …
computations. Many previous studies aimed to visualize the selectivity of individual units by …
[HTML][HTML] Invariant visual object recognition: biologically plausible approaches
L Robinson, ET Rolls - Biological cybernetics, 2015 - Springer
Key properties of inferior temporal cortex neurons are described, and then, the biological
plausibility of two leading approaches to invariant visual object recognition in the ventral …
plausibility of two leading approaches to invariant visual object recognition in the ventral …
Learning visual spatial pooling by strong PCA dimension reduction
H Hosoya, A Hyvärinen - Neural computation, 2016 - direct.mit.edu
In visual modeling, invariance properties of visual cells are often explained by a pooling
mechanism, in which outputs of neurons with similar selectivities to some stimulus …
mechanism, in which outputs of neurons with similar selectivities to some stimulus …
Learning image representations tied to egomotion from unlabeled video
D Jayaraman, K Grauman - International Journal of Computer Vision, 2017 - Springer
Understanding how images of objects and scenes behave in response to specific
egomotions is a crucial aspect of proper visual development, yet existing visual learning …
egomotions is a crucial aspect of proper visual development, yet existing visual learning …