Deep Cauchy Hashing for Hamming Space Retrieval

By Mingsheng Long, Bin Liu, Jianmin Wang. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018

336 citations recorded by the source corpus.

Due to its computation efficiency and retrieval quality, hashing has been widely applied to approximate nearest neighbor search for large-scale image retrieval, while deep hashing further improves the retrieval quality by end-to-end representation learning and hash coding. With compact hash codes, Hamming space retrieval enables the most efficient constant-time search that returns data points within a given Hamming radius to each query, by hash table lookups instead of linear scan. However, subject to the weak capability of concentrating relevant images to be within a small Hamming ball due to mis-specified loss functions, existing deep hashing methods may underperform for Hamming space retrieval. This work presents Deep Cauchy Hashing (DCH), a novel deep hashing model that generates compact and concentrated binary hash codes to enable efficient and effective Hamming space retrieval. The main idea is to design a pairwise cross-entropy loss based on Cauchy distribution, which penalizes significantly on similar image pairs with Hamming distance larger than the given Hamming radius threshold. Comprehensive experiments demonstrate that DCH can generate highly concentrated hash codes and yield state-of-the-art Hamming space retrieval performance on three datasets, NUS-WIDE, CIFAR-10, and MS-COCO.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e7b92fc6e2f1a13a3076a48a78e03badacb0465b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Jiashi Feng
3. Cheng Deng
4. Shiv Ram Dubey
5. Luc Van Gool
6. Shuicheng Yan
7. Li Yuan
8. Tongliang Liu

Citations in the corpus

• A Decade Survey of Content Based Image Retrieval Using Deep Learning (2020, methodology): “have investigated a deep cauchy hashing (DCH) model for binary hash code with the help of a pairwise cross-entropy loss based on Cauchy distribution [81].”
• Self-supervised Image-text Pre-training With Mixed Data In Chest X-rays (2021, methodology): “D pooled version of F img and F txt for generating a 64-bit hashing code and adopt the Cauchy hashing loss [4] for the training.”
• Two-Stream Deep Hashing With Class-Specific Centers for Supervised Image Search (2020, methodology): “Deep Cauchy hashing [60] adopts Cauchy distribution to continue to optimize data pairs in a relatively small Hamming ball, which are difficult to optimize effectively using traditional loss functions.”
• Deep Bayesian Hashing with Center Prior for Multi-modal Neuroimage Retrieval (2020, methodology): “Similar to [50], [51], we select the hyper-parameter α via cross-validation.”
• Deep Multi-View Enhancement Hashing for Image Retrieval (2020, methodology): “In recent years, several convolution artificial neural network hash methods [5], [6], [7], [8], [9] which show significant improvement in the image retrieval task have been proposed.”
• Central Similarity Quantization for Efficient Image and Video Retrieval (2019, methodology): “The “deep learning to hash” methods such as CNNH [44], DNNH [14], DHN [48], DCH [1] and Hash-Net [2] have been successfully applied to image hashing.”