SUBIC: A supervised, structured binary code for image search

TL;DR

This paper introduces SUBIC, a supervised deep learning method that produces structured binary codes for image search, outperforming existing compact representations in various retrieval tasks.

Contribution

The paper presents a novel supervised deep learning approach with a block-softmax and entropy losses to generate structured binary codes for visual search.

Findings

Outperforms state-of-the-art deep hashing methods in image retrieval

Effective in cross-domain category retrieval and classification

Provides publicly available code and models

Abstract

For large-scale visual search, highly compressed yet meaningful representations of images are essential. Structured vector quantizers based on product quantization and its variants are usually employed to achieve such compression while minimizing the loss of accuracy. Yet, unlike binary hashing schemes, these unsupervised methods have not yet benefited from the supervision, end-to-end learning and novel architectures ushered in by the deep learning revolution. We hence propose herein a novel method to make deep convolutional neural networks produce supervised, compact, structured binary codes for visual search. Our method makes use of a novel block-softmax non-linearity and of batch-based entropy losses that together induce structure in the learned encodings. We show that our method outperforms state-of-the-art compact representations based on deep hashing or structured quantization in single and cross-domain category retrieval, instance retrieval and classification. We make our code and models publicly available online.