Fast Class-wise Updating for Online Hashing
Mingbao Lin, Rongrong Ji, Xiaoshuai Sun, Baochang Zhang, Feiyue Huang,, Yonghong Tian, Dacheng Tao

TL;DR
This paper introduces FCOH, a fast and efficient supervised online hashing method that updates hash functions class-wise using a semi-relaxation optimization, significantly improving adaptivity, efficiency, and storage over existing methods.
Contribution
The paper proposes a novel class-wise updating scheme with semi-relaxation optimization for online hashing, enhancing adaptivity, reducing training time, and saving storage compared to prior approaches.
Findings
Achieves at least 75% storage saving.
Significantly reduces online training time.
Outperforms state-of-the-art methods in experiments.
Abstract
Online image hashing has received increasing research attention recently, which processes large-scale data in a streaming fashion to update the hash functions on-the-fly. To this end, most existing works exploit this problem under a supervised setting, i.e., using class labels to boost the hashing performance, which suffers from the defects in both adaptivity and efficiency: First, large amounts of training batches are required to learn up-to-date hash functions, which leads to poor online adaptivity. Second, the training is time-consuming, which contradicts with the core need of online learning. In this paper, a novel supervised online hashing scheme, termed Fast Class-wise Updating for Online Hashing (FCOH), is proposed to address the above two challenges by introducing a novel and efficient inner product operation. To achieve fast online adaptivity, a class-wise updating method is…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Image and Video Retrieval Techniques · Video Surveillance and Tracking Methods · Caching and Content Delivery
