Deep Collaborative Discrete Hashing With Semantic-invariant Structure

Abstract

Existing deep hashing approaches fail to fully explore semantic correlations and neglect the effect of linguistic context on visual attention learning, leading to inferior performance. This paper proposes a dual-stream learning framework, dubbed Deep Collaborative Discrete Hashing (DCDH), which constructs a discriminative common discrete space by collaboratively incorporating the shared and individual semantics deduced from visual features and semantic labels. Specifically, the context-aware representations are generated by employing the outer product of visual embeddings and semantic encodings. Moreover, we reconstruct the labels and introduce the focal loss to take advantage of frequent and rare concepts. The common binary code space is built on the joint learning of the visual representations attended by language, the semantic-invariant structure construction and the label distribution correction. Extensive experiments demonstrate the superiority of our method.

Stats

• citations11
• S2 citations—
• github stars0
• HF likes0
• heat score8.09
• arxiv keywang2019deep

Related papers

• Unsupervised Deep Cross-modality Spectral Hashing (2020)11.39
• Deep Supervised Discrete Hashing (2017)0.00
• Exploring Auxiliary Context: Discrete Semantic Transfer Hashing For Scalable Image Retrieval (2019)15.88
• Deep Discrete Hashing With Self-supervised Pairwise Labels (2017)9.49
• Unsupervised Semantic Deep Hashing (2018)10.48
• Deep Unsupervised Hashing With Latent Semantic Components (2022)10.74
• Discriminative Supervised Hashing For Cross-modal Similarity Search (2018)7.81
• Deep Class-wise Hashing: Semantics-preserving Hashing Via Class-wise Loss (2018)11.19