DeepAI AI Chat
Log In Sign Up

Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings

by   Pedro Morgado, et al.

Image hash codes are produced by binarizing the embeddings of convolutional neural networks (CNN) trained for either classification or retrieval. While proxy embeddings achieve good performance on both tasks, they are non-trivial to binarize, due to a rotational ambiguity that encourages non-binary embeddings. The use of a fixed set of proxies (weights of the CNN classification layer) is proposed to eliminate this ambiguity, and a procedure to design proxy sets that are nearly optimal for both classification and hashing is introduced. The resulting hash-consistent large margin (HCLM) proxies are shown to encourage saturation of hashing units, thus guaranteeing a small binarization error, while producing highly discriminative hash-codes. A semantic extension (sHCLM), aimed to improve hashing performance in a transfer scenario, is also proposed. Extensive experiments show that sHCLM embeddings achieve significant improvements over state-of-the-art hashing procedures on several small and large datasets, both within and beyond the set of training classes.


Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks

This paper presents a simple yet effective supervised deep hash approach...

Deep Cross-modal Proxy Hashing

Due to their high retrieval efficiency and low storage cost for cross-mo...

ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks

Hash codes are efficient data representations for coping with the ever g...

From Hashing to CNNs: Training BinaryWeight Networks via Hashing

Deep convolutional neural networks (CNNs) have shown appealing performan...

Unsupervised Deep Image Hashing through Tag Embeddings

Many approaches to semantic image hashing have been formulated as superv...

SHOE: Supervised Hashing with Output Embeddings

We present a supervised binary encoding scheme for image retrieval that ...

Hash Embeddings for Efficient Word Representations

We present hash embeddings, an efficient method for representing words i...