PDF] Locality-sensitive binary codes from shift-invariant kernels

This paper introduces a simple distribution-free encoding scheme based on random projections, such that the expected Hamming distance between the binary codes of two vectors is related to the value of a shift-invariant kernel between the vectors. This paper addresses the problem of designing binary codes for high-dimensional data such that vectors that are similar in the original space map to similar binary strings. We introduce a simple distribution-free encoding scheme based on random projections, such that the expected Hamming distance between the binary codes of two vectors is related to the value of a shift-invariant kernel (e.g., a Gaussian kernel) between the vectors. We present a full theoretical analysis of the convergence properties of the proposed scheme, and report favorable experimental performance as compared to a recent state-of-the-art method, spectral hashing.

Hyperspectral imaging for classification of bulk grain samples with deep convolutional neural networks - Erik Schou Dreier, Klavs Martin Sorensen, Toke Lund-Hansen, Birthe Møller Jespersen, Kim Steenstrup Pedersen, 2022

PDF) Unsupervised Ensemble Hashing: Boosting Minimum Hamming Distance

Invariant Node Representation Learning under Distribution Shifts with Multiple Latent Environments

Population codes enable learning from few examples by shaping inductive bias

Kernel locality‐constrained sparse coding for head pose estimation - Kim - 2016 - IET Computer Vision - Wiley Online Library

Population codes enable learning from few examples by shaping inductive bias

A spatiotemporal mechanism of visual attention: Superdiffusive motion and theta oscillations of neural population activity patterns

PDF] Iterative quantization: A procrustean approach to learning binary codes

A Complete List of All Adversarial Example Papers