Focus of Attention Improves Information Transfer in Visual Features
Matteo Tiezzi, Stefano Melacci, Alessandro Betti, Marco Maggini, Marco Gori
Abstract
Unsupervised learning from continuous visual streams is a challenging problem that cannot be naturally and efficiently managed in the classic batch-mode setting of computation. The information stream must be carefully processed accordingly to an appropriate spatio-temporal distribution of the visual data, while most approaches of learning commonly assume uniform probability density. In this paper we focus on unsupervised learning for transferring visual information in a truly online setting by using a computational model that is inspired to the principle of least action in physics. The maximization of the mutual information is carried out by a temporal process which yields online estimation of the entropy terms. The model, which is based on second-order differential equations, maximizes the information transfer from the input to a discrete space of symbols related to the visual features of the input, whose computation is supported by hidden neurons. In order to better structure the input probability distribution, we use a human-like focus of attention model that, coherently with the information maximization model, is also based on second-order differential equations. We provide experimental results to support the theory by showing that the spatio-temporal filtering induced by the focus of attention allows the system to globally transfer more information from the input stream over the focused areas and, in some contexts, over the whole frames with respect to the unfiltered case that yields uniform probability distributions.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on1
Related papers
- Entropy-driven Unsupervised Keypoint Representation Learning in VideosAli Younes, Simone Schaub-Meyer, Georgia ChalvatzakiICML 2023 · 1 citation
- Temporal-wise Attention Spiking Neural Networks for Event Streams ClassificationMan Yao, Huanhuan Gao, Guangshe Zhao, Dingheng Wang et al.ICCV 2021 · 225 citations
- Biologically Inspired Learning Model for Instructed VisionRoy Abel, Shimon UllmanNeurIPS 2024 · 4 citations
- Wiring Up Vision: Minimizing Supervised Synaptic Updates Needed to Produce a Primate Ventral StreamFranziska Geiger, Martin Schrimpf, Tiago Marques, James J. DiCarloICLR 2022 · 14 citations
- A Dual-Stream Neural Network Explains the Functional Segregation of Dorsal and Ventral Visual Pathways in Human BrainsMinkyu Choi, Kuan Han, Xiaokai Wang, Yizhen Zhang et al.NeurIPS 2023 · 33 citations
