Learning A Deep ℓ∞ Encoder for Hashing

Abstract

We investigate the `1-constrained representation which demonstrates robustness to quantization errors, utilizing the tool of deep learning. Based on the Alternating Direction Method of Multipliers (ADMM), we formulate the original convex minimization problem as a feed-forward neural network, named Deep `1 Encoder, by introducing the novel Bounded Linear… (More)

9 Figures and Tables

Topics

  • Presentations referencing similar topics