Weakly Supervised Deep Image Hashing Through Tag Embeddings

Abstract

Many approaches to semantic image hashing have been formulated as supervised learning problems that utilize images and label information to learn the binary hash codes. However, large-scale labeled image data is expensive to obtain, thus imposing a restriction on the usage of such algorithms. On the other hand, unlabelled image data is abundant due to the existence of many Web image repositories. Such Web images may often come with images tags that contain useful information, although raw tags, in general, do not readily lead to semantic labels. Motivated by this scenario, we formulate the problem of semantic image hashing as a weakly-supervised learning problem. We utilize the information contained in the user-generated tags associated with the images to learn the hash codes. More specifically, we extract the word2vec semantic embeddings of the tags and use the information contained in them for constraining the learning. Accordingly, we name our model Weakly Supervised Deep Hashing us

Stats

• citations31
• S2 citations—
• github stars0
• HF likes0
• heat score11.29
• arxiv keygattupalli2018weakly

Related papers

• Weakly-supervised Online Hashing (2020)7.50
• Deep Reinforcement Learning With Label Embedding Reward For Supervised Image Hashing (2020)0.00
• Deep Class-wise Hashing: Semantics-preserving Hashing Via Class-wise Loss (2018)11.19
• Unsupervised Semantic Deep Hashing (2018)10.48
• Dual-level Semantic Transfer Deep Hashing For Efficient Social Image Retrieval (2020)12.33
• SSDH: Semi-supervised Deep Hashing For Large Scale Image Retrieval (2016)15.40
• Deep Supervised Discrete Hashing (2017)0.00
• SHREWD: Semantic Hierarchy-based Relational Embeddings For Weakly-supervised Deep Hashing (2019)0.00