# Transformer-based Clipped Contrastive Quantization Learning for Unsupervised Image Retrieval

arXiv: https://arxiv.org/abs/2401.15362 · HTML: https://mlsanity.com/paper/2401.15362/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 27 Jan 2024.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Debiased Contrastive Learning](https://mlsanity.com/paper/2007.00224/) (2020)
- [Central Similarity Quantization for Efficient Image and Video Retrieval](https://mlsanity.com/paper/1908.00347/) (2019)
- [A Decade Survey of Content Based Image Retrieval using Deep Learning](https://mlsanity.com/paper/2012.00641/) (2020)
- [Self-supervised Product Quantization for Deep Unsupervised Image Retrieval](https://mlsanity.com/paper/2109.02244/) (2021)
- [Auto-Encoding Twin-Bottleneck Hashing](https://mlsanity.com/paper/2002.11930/) (2020)
- [Unsupervised Hashing with Contrastive Information Bottleneck](https://mlsanity.com/paper/2105.06138/) (2021)
- [Deep Unsupervised Image Hashing by Maximizing Bit Entropy](https://mlsanity.com/paper/2012.12334/) (2020)
- [Contrastive Quantization with Code Memory for Unsupervised Image Retrieval](https://mlsanity.com/paper/2109.05205/) (2021)
- [ViT2Hash: Unsupervised Information-Preserving Hashing](https://mlsanity.com/paper/2201.05541/) (2022)

## Abstract (arXiv)

Unsupervised image retrieval aims to learn the important visual characteristics without any given level to retrieve the similar images for a given query image. The Convolutional Neural Network (CNN)-based approaches have been extensively exploited with self-supervised contrastive learning for image hashing. However, the existing approaches suffer due to lack of effective utilization of global features by CNNs and biased-ness created by false negative pairs in the contrastive learning. In this paper, we propose a TransClippedCLR model by encoding the global context of an image using Transformer having local context through patch based processing, by generating the hash codes through product quantization and by avoiding the potential false negative pairs through clipped contrastive learning. The proposed model is tested with superior performance for unsupervised image retrieval on benchmark datasets, including CIFAR10, NUS-Wide and Flickr25K, as compared to the recent state-of-the-art deep models. The results using the proposed clipped contrastive learning are greatly improved on all datasets as compared to same backbone network with vanilla contrastive learning.