Unsupervised Triplet Hashing for Fast Image Retrieval

Huang, Shanshan; Xiong, Yan; Zhang, Ya; Wang, Jia

doi:10.1145/3126686.3126773

Cited by 43 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the second stage, the pseudo labels are used as soft supervisions to train a deep hashing network and minimize the classification loss and quantization loss. Unsupervised triplet hashing (UTH) [33] proposed to construct the image triplet by an anchor image, a rotated image, and a random image. Similarity-adaptive deep hashing (SADH) [13] proposed to train hashing model alternatively over three modules, which substantially improves the robustness of binary codes optimization.…”

Section: A Unsupervised Deep Hashing Methodsmentioning

confidence: 99%

Contrastive Self-Supervised Hashing With Dual Pseudo Agreement

Wang

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Recently, unsupervised deep hashing has attracted increasing attention, mainly because of its potential ability to learn binary codes without identity annotations. However, because the labels are predicted by their pretext tasks, unsupervised deep hashing becomes unstable when learning with noisy labels. To mitigate this issue, we propose a simple but effective approach to self-supervised hash learning based on dual pseudo agreement. By adding a consistency constraint, our method can prevent corrupted labels and encourage generalization for effective knowledge distillation. Specifically, we use the refined pseudo labels as a stabilization constraint to train hash codes, which can implicitly encode semantic structures of the data into the learned Hamming space. Based on the stable pseudo labels, we propose a self-supervised hashing method with mutual information and noise contrastive loss. Throughout the process of hash learning, the stable pseudo labels and data distributions collaboratively work together as teachers to guide the binary codes learning process. Extensive experiments on three publicly available datasets demonstrate that the proposed method can consistently outperform state-of-the-art methods by large margins. INDEX TERMS Unsupervised hashing, self-supervised learning, pseudo labels, mutual information.

show abstract

Section: A Unsupervised Deep Hashing Methodsmentioning

confidence: 99%

Contrastive Self-Supervised Hashing With Dual Pseudo Agreement

Wang

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Discriminative attributes representations (DAR) [25] firstly trains a CNN coupled with unsupervised discriminative clustering and then utilizes the cluster membership as a soft supervision to learn hash functions. Unsupervised triplet hashing (UTH) [26] exploits an unsupervised triplet loss to minimize the distance between an anchor image and its rotated version, while maximize the distance between the anchor image and a random image. HashGAN [14] adopts three networks including a generator, a discriminator, and an encoder to learn hash functions.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Deep Pairwise Hashing

Shi

et al. 2022

Electronics

View full text Add to dashboard Cite

Although unsupervised deep hashing is potentially very useful for tackling many large-scale tasks, its performance is still far below satisfactory. Additionally, its performance might be significantly improved by effectively exploiting the pair similarity relationship among training data, but the attained similarity matrix usually contains noisy information, which often largely decreases the model performance. To alleviate this issue, in this paper, we propose a novel unsupervised deep pairwise hashing method to effectively and robustly exploit the similarity information between training samples and multiple anchors. We first create an ensemble anchor-based pairwise similarity matrix to enhance the robustness of similarity and dissimilarity relations between training samples and anchors. Afterwards, we propose a novel loss function to directly and robustly take advantage of the similarity and dissimilarity information via a weighted cross-entropy loss, and make use of a square loss to reduce the gap between latent binary vectors and binary codes, and another square loss to form consensus predictions of latent binary vectors. Extensive experiments on large-scale benchmark databases demonstrate the effectiveness of the proposed method, which outperforms recent state-of-the-art unsupervised hashing methods with significantly better ranking performance.

show abstract

“…With the rapidly growth of image data, data-dependent hashing methods have attracted more and more attention, due to their high retrieval efficiency and low storage cost. Roughly speaking, datadependent hashing methods can be divided into two categories: unsupervised methods [7,21,24,26,31,35] and supervised methods [3,11,17,20,25,27]. Among the existing supervised hashing methods, deep supervised hashing methods [1,6,9,16,23,25] have shown state-of-the-art performance by integrating feature learning and hash code learning into an end-to-end network to generate high-quality hash codes.…”

Section: Introductionmentioning

confidence: 99%

Weighted Gaussian Loss based Hamming Hashing

Mao

Kong

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Recently, deep Hamming hashing methods have been proposed for Hamming space retrieval which enables constant-time search by hash table lookups instead of linear scan. When carrying out Hamming space retrieval, for each query datapoint, there is a Hamming ball centered on the query datapoint, and only the datapoints within the Hamming ball are returned as the relevant ones, while those beyond are discarded directly. Thus, to further enhance the retrieval performance, it is a key point for the Hamming hashing methods to decrease the dissimilar datapoints within the Hamming ball. However, nearly all existing Hamming hashing methods cannot effectively penalize the dissimilar pairs within the Hamming ball to push them out. To tackle this problem, in this paper, we propose a novel Weighted Gaussian Loss based Hamming Hashing, called WGLHH, which introduces a weighted Gaussian loss to optimize hashing model. Specifically, the weighted Gaussian loss consists of three parts: a novel Gaussian-distribution based loss, a novel badly-trained-pair attention mechanism and a quantization loss. The Gaussian-distribution based loss is proposed to effectively

show abstract

Unsupervised Triplet Hashing for Fast Image Retrieval

Cited by 43 publications

References 16 publications

Contrastive Self-Supervised Hashing With Dual Pseudo Agreement

Contrastive Self-Supervised Hashing With Dual Pseudo Agreement

Unsupervised Deep Pairwise Hashing

Weighted Gaussian Loss based Hamming Hashing

Contact Info

Product

Resources

About