UniHash: Unifying Pointwise and Pairwise Hashing Paradigms for Seen and Unseen Category Retrieval

• URL: http://arxiv.org/abs/2601.09828v2
• Date: Tue, 20 Jan 2026 16:21:08 GMT
• Title: UniHash: Unifying Pointwise and Pairwise Hashing Paradigms for Seen and Unseen Category Retrieval
• Authors: Xiaoxu Ma, Runhao Li, Xiangbo Zhang, Zhenyu Weng,
• Abstract summary: We propose Unified Hashing (UniHash) to achieve balanced retrieval performance across seen and unseen categories.<n>UniHash consists of two complementary branches: a center-based branch following the pointwise paradigm and a pairwise branch following the pairwise paradigm.<n>A novel hash code learning method is introduced to enable bidirectional knowledge transfer between branches, improving hash code discriminability and generalization.
• Score: 8.167530874832106
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Effective retrieval across both seen and unseen categories is crucial for modern image retrieval systems. Retrieval on seen categories ensures precise recognition of known classes, while retrieval on unseen categories promotes generalization to novel classes with limited supervision. However, most existing deep hashing methods are confined to a single training paradigm, either pointwise or pairwise, where the former excels on seen categories and the latter generalizes better to unseen ones. To overcome this limitation, we propose Unified Hashing (UniHash), a dual-branch framework that unifies the strengths of both paradigms to achieve balanced retrieval performance across seen and unseen categories. UniHash consists of two complementary branches: a center-based branch following the pointwise paradigm and a pairwise branch following the pairwise paradigm. A novel hash code learning method is introduced to enable bidirectional knowledge transfer between branches, improving hash code discriminability and generalization. It employs a mutual learning loss to align hash representations and introduces a Split-Merge Mixture of Hash Experts (SM-MoH) module to enhance cross-branch exchange of hash representations. Theoretical analysis substantiates the effectiveness of UniHash, and extensive experiments on CIFAR-10, MSCOCO, and ImageNet demonstrate that UniHash consistently achieves state-of-the-art performance in both seen and unseen image retrieval scenarios.

Related papers

• Mutual Learning for Hashing: Unlocking Strong Hash Functions from Weak Supervision [8.509518175943537]
  Mutual Learning for Hashing (MLH) is a weak-to-strong framework that enhances a center-based hashing branch by transferring knowledge from a weaker pairwise-based branch.<n> MLH consistently outperforms state-of-the-art hashing methods across multiple benchmark datasets.
  arXiv  Detail & Related papers  (2025-10-09T02:39:05Z)
• Hashing-Baseline: Rethinking Hashing in the Age of Pretrained Models [4.531902882476647]
  We introduce Hashing-Baseline, a strong training-free hashing method leveraging powerful pretrained encoders that produce rich pretrained embeddings.<n>Our approach combines these techniques with frozen embeddings from state-of-the-art vision and audio encoders to yield competitive retrieval performance without any additional learning or fine-tuning.
  arXiv  Detail & Related papers  (2025-09-17T20:58:43Z)
• Deep Hashing with Semantic Hash Centers for Image Retrieval [15.771584515999283]
  This paper introduces the concept of semantic hash centers, building on the idea of traditional hash centers.<n>We develop a classification network to identify semantic similarities between classes using a data-dependent similarity calculation.<n>Second, we introduce an optimization algorithm to generate semantic hash centers, preserving semantic relatedness while enforcing a minimum distance between centers to avoid excessively similar hash codes.
  arXiv  Detail & Related papers  (2025-07-11T08:22:27Z)
• Learning to Hash for Recommendation: A Survey [49.943390288789494]
  This survey provides a comprehensive overview of state-of-the-art HashRec algorithms.<n>We categorize existing works into a three-tier taxonomy based on: (i) learning objectives, (ii) optimization strategies, and (iii) recommendation scenarios.
  arXiv  Detail & Related papers  (2024-12-05T05:07:19Z)
• Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery [65.16724941038052]
  Category-aware Prototype Generation (CPG) and Discrimi Category 5.3% (DCE) are proposed.<n>CPG enables the model to fully capture the intra-category diversity by representing each category with multiple prototypes.<n>DCE boosts the discrimination ability of hash code with the guidance of the generated category prototypes.
  arXiv  Detail & Related papers  (2024-10-24T23:51:40Z)
• ConceptHash: Interpretable Fine-Grained Hashing via Concept Discovery [128.30514851911218]
  ConceptHash is a novel method that achieves sub-code level interpretability. In ConceptHash, each sub-code corresponds to a human-understandable concept, such as an object part. We incorporate language guidance to ensure that the learned hash codes are distinguishable within fine-grained object classes.
  arXiv  Detail & Related papers  (2024-06-12T17:49:26Z)
• CoopHash: Cooperative Learning of Multipurpose Descriptor and Contrastive Pair Generator via Variational MCMC Teaching for Supervised Image Hashing [42.67510119856105]
  generative models, such as Generative Adversarial Networks (GANs), can generate synthetic data in an image hashing model. GANs are difficult to train, which prevents hashing approaches from jointly training the generative models and the hash functions. We propose a novel framework, the generative cooperative hashing network, which is based on energy-based cooperative learning.
  arXiv  Detail & Related papers  (2022-10-09T15:42:36Z)
• Deep Asymmetric Hashing with Dual Semantic Regression and Class Structure Quantization [9.539842235137376]
  We propose a dual semantic asymmetric hashing (DSAH) method, which generates discriminative hash codes under three-fold constrains. With these three main components, high-quality hash codes can be generated through network.
  arXiv  Detail & Related papers  (2021-10-24T16:14:36Z)
• CIMON: Towards High-quality Hash Codes [63.37321228830102]
  We propose a new method named textbfComprehensive stextbfImilarity textbfMining and ctextbfOnsistency leartextbfNing (CIMON) First, we use global refinement and similarity statistical distribution to obtain reliable and smooth guidance. Second, both semantic and contrastive consistency learning are introduced to derive both disturb-invariant and discriminative hash codes.
  arXiv  Detail & Related papers  (2020-10-15T14:47:14Z)
• Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings [65.36757931982469]
  Image hash codes are produced by binarizing embeddings of convolutional neural networks (CNN) trained for either classification or retrieval. The use of a fixed set of proxies (weights of the CNN classification layer) is proposed to eliminate this ambiguity. The resulting hash-consistent large margin (HCLM) proxies are shown to encourage saturation of hashing units, thus guaranteeing a small binarization error.
  arXiv  Detail & Related papers  (2020-07-27T23:47:43Z)
• Reinforcing Short-Length Hashing [61.75883795807109]
  Existing methods have poor performance in retrieval using an extremely short-length hash code. In this study, we propose a novel reinforcing short-length hashing (RSLH) In this proposed RSLH, mutual reconstruction between the hash representation and semantic labels is performed to preserve the semantic information. Experiments on three large-scale image benchmarks demonstrate the superior performance of RSLH under various short-length hashing scenarios.
  arXiv  Detail & Related papers  (2020-04-24T02:23:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.