Instance-weighted Central Similarity For Multi-label Image Retrieval

Abstract

Deep hashing has been widely applied to large-scale image retrieval by encoding high-dimensional data points into binary codes for efficient retrieval. Compared with pairwise/triplet similarity based hash learning, central similarity based hashing can more efficiently capture the global data distribution. For multi-label image retrieval, however, previous methods only use multiple hash centers with equal weights to generate one centroid as the learning target, which ignores the relationship between the weights of hash centers and the proportion of instance regions in the image. To address the above issue, we propose a two-step alternative optimization approach, Instance-weighted Central Similarity (ICS), to automatically learn the center weight corresponding to a hash code. Firstly, we apply the maximum entropy regularizer to prevent one hash center from dominating the loss function, and compute the center weights via projection gradient descent. Secondly, we update neural network para

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2021instance

Related papers

• Improved Deep Classwise Hashing With Centers Similarity Learning For Image Retrieval (2021)5.84
• Improved Deep Hashing With Soft Pairwise Similarity For Multi-label Image Retrieval (2018)16.82
• Hierarchy Neighborhood Discriminative Hashing For An Unified View Of Single-label And Multi-label Image Retrieval (2019)0.00
• Central Similarity Quantization For Efficient Image And Video Retrieval (2019)23.49
• Deep Hashing With Semantic Hash Centers For Image Retrieval (2025)2.26
• Deep Self-adaptive Hashing For Image Retrieval (2021)8.35
• Query-adaptive Image Retrieval By Deep Weighted Hashing (2016)12.68
• Deep Class-wise Hashing: Semantics-preserving Hashing Via Class-wise Loss (2018)11.19