End-to-end Binary Representation Learning Via Direct Binary Embedding

Abstract

Learning binary representation is essential to large-scale computer vision tasks. Most existing algorithms require a separate quantization constraint to learn effective hashing functions. In this work, we present Direct Binary Embedding (DBE), a simple yet very effective algorithm to learn binary representation in an end-to-end fashion. By appending an ingeniously designed DBE layer to the deep convolutional neural network (DCNN), DBE learns binary code directly from the continuous DBE layer activation without quantization error. By employing the deep residual network (ResNet) as DCNN component, DBE captures rich semantics from images. Furthermore, in the effort of handling multilabel images, we design a joint cross entropy loss that includes both softmax cross entropy and weighted binary cross entropy in consideration of the correlation and independence of labels, respectively. Extensive experiments demonstrate the significant superiority of DBE over state-of-the-art methods on tasks

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keyliu2017end

Related papers

• Embarrassingly Simple Binary Representation Learning (2019)9.41
• Supervised Hashing With End-to-end Binary Deep Neural Network (2017)2.26
• 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
• Deep Reinforcement Learning With Label Embedding Reward For Supervised Image Hashing (2020)0.00
• Discriminative Cross-view Binary Representation Learning (2018)4.52
• Learning To Hash With Binary Deep Neural Network (2016)14.93
• Recurrent Binary Embedding For Gpu-enabled Exhaustive Retrieval From Billion-scale Semantic Vectors (2018)8.35