Embarrassingly Simple Binary Representation Learning

Abstract

Recent binary representation learning models usually require sophisticated binary optimization, similarity measure or even generative models as auxiliaries. However, one may wonder whether these non-trivial components are needed to formulate practical and effective hashing models. In this paper, we answer the above question by proposing an embarrassingly simple approach to binary representation learning. With a simple classification objective, our model only incorporates two additional fully-connected layers onto the top of an arbitrary backbone network, whilst complying with the binary constraints during training. The proposed model lower-bounds the Information Bottleneck (IB) between data samples and their semantics, and can be related to many recent `learning to hash' paradigms. We show that, when properly designed, even such a simple network can generate effective binary codes, by fully exploring data semantics without any held-out alternating updating steps or auxiliary models. Ex

Stats

• citations17
• S2 citations—
• github stars0
• HF likes0
• heat score9.41
• arxiv keyshen2019embarrassingly

Related papers

• Learning To Hash With Binary Deep Neural Network (2016)14.93
• Compact Hash Code Learning With Binary Deep Neural Network (2017)9.03
• Binary Constrained Deep Hashing Network For Image Retrieval Without Manual Annotation (2018)5.84
• Unsupervised Hashing With Contrastive Information Bottleneck (2021)13.50
• End-to-end Binary Representation Learning Via Direct Binary Embedding (2017)5.84
• One Loss For All: Deep Hashing With A Single Cosine Similarity Based Learning Objective (2021)3.99
• Binary Representation Via Jointly Personalized Sparse Hashing (2022)9.59
• Structured Learning Of Binary Codes With Column Generation (2016)0.00