Vit2hash: Unsupervised Information-preserving Hashing

Abstract

Unsupervised image hashing, which maps images into binary codes without supervision, is a compressor with a high compression rate. Hence, how to preserving meaningful information of the original data is a critical problem. Inspired by the large-scale vision pre-training model, known as ViT, which has shown significant progress for learning visual representations, in this paper, we propose a simple information-preserving compressor to finetune the ViT model for the target unsupervised hashing task. Specifically, from pixels to continuous features, we first propose a feature-preserving module, using the corrupted image as input to reconstruct the original feature from the pre-trained ViT model and the complete image, so that the feature extractor can focus on preserving the meaningful information of original data. Secondly, from continuous features to hash codes, we propose a hashing-preserving module, which aims to keep the semantic information from the pre-trained ViT model by using th

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygong2022vit2hash

Related papers

• Transhash: Transformer-based Hamming Hashing For Efficient Image Retrieval (2021)13.44
• Vision Transformer Hashing For Image Retrieval (2021)17.01
• Dual-stream Knowledge-preserving Hashing For Unsupervised Video Retrieval (2023)9.23
• Unsupervised Hashing With Contrastive Information Bottleneck (2021)13.50
• Unsupervised Semantic Deep Hashing (2018)10.48
• Bilinear Supervised Hashing Based On 2D Image Features (2019)8.60
• Unsupervised Deep Hashing For Large-scale Visual Search (2016)9.59
• Simultaneous Feature Aggregating And Hashing For Compact Binary Code Learning (2019)9.92