Vision Transformer Hashing For Image Retrieval

Abstract

Deep learning has shown a tremendous growth in hashing techniques for image retrieval. Recently, Transformer has emerged as a new architecture by utilizing self-attention without convolution. Transformer is also extended to Vision Transformer (ViT) for the visual recognition with a promising performance on ImageNet. In this paper, we propose a Vision Transformer based Hashing (VTS) for image retrieval. We utilize the pre-trained ViT on ImageNet as the backbone network and add the hashing head. The proposed VTS model is fine tuned for hashing under six different image retrieval frameworks, including Deep Supervised Hashing (DSH), HashNet, GreedyHash, Improved Deep Hashing Network (IDHN), Deep Polarized Network (DPN) and Central Similarity Quantization (CSQ) with their objective functions. We perform the extensive experiments on CIFAR10, ImageNet, NUS-Wide, and COCO datasets. The proposed VTS based image retrieval outperforms the recent state-of-the-art hashing techniques with a great ma

Stats

• citations67
• S2 citations—
• github stars42
• HF likes0
• heat score17.01
• arxiv keydubey2021vision

Related papers

• Transhash: Transformer-based Hamming Hashing For Efficient Image Retrieval (2021)13.44
• Hybridhash: Hybrid Convolutional And Self-attention Deep Hashing For Image Retrieval (2024)12.56
• Training Vision Transformers For Image Retrieval (2021)0.00
• Unsupervised Triplet Hashing For Fast Image Retrieval (2017)12.10
• Boosting Vision Transformers For Image Retrieval (2022)15.28
• Vit2hash: Unsupervised Information-preserving Hashing (2022)0.00
• Investigating The Vision Transformer Model For Image Retrieval Tasks (2021)10.74
• Leveraging High-resolution Features For Improved Deep Hashing-based Image Retrieval (2024)4.52