Instance-weighted Central Similarity for Multi-label Image Retrieval
- URL: http://arxiv.org/abs/2108.05274v1
- Date: Wed, 11 Aug 2021 15:18:18 GMT
- Title: Instance-weighted Central Similarity for Multi-label Image Retrieval
- Authors: Zhiwei Zhang and Hanyu Peng and Hongsheng Li
- Abstract summary: We propose Instance-weighted Central Similarity (ICS) to automatically learn the center weight corresponding to a hash code.
Our method achieves the state-of-the-art performance on the image retrieval benchmarks, and especially improves the mAP by 1.6%-6.4% on the MS COCO dataset.
- Score: 66.23348499938278
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep hashing has been widely applied to large-scale image retrieval by
encoding high-dimensional data points into binary codes for efficient
retrieval. Compared with pairwise/triplet similarity based hash learning,
central similarity based hashing can more efficiently capture the global data
distribution. For multi-label image retrieval, however, previous methods only
use multiple hash centers with equal weights to generate one centroid as the
learning target, which ignores the relationship between the weights of hash
centers and the proportion of instance regions in the image. To address the
above issue, we propose a two-step alternative optimization approach,
Instance-weighted Central Similarity (ICS), to automatically learn the center
weight corresponding to a hash code. Firstly, we apply the maximum entropy
regularizer to prevent one hash center from dominating the loss function, and
compute the center weights via projection gradient descent. Secondly, we update
neural network parameters by standard back-propagation with fixed center
weights. More importantly, the learned center weights can well reflect the
proportion of foreground instances in the image. Our method achieves the
state-of-the-art performance on the image retrieval benchmarks, and especially
improves the mAP by 1.6%-6.4% on the MS COCO dataset.
Related papers
- A Weighted K-Center Algorithm for Data Subset Selection [70.49696246526199]
Subset selection is a fundamental problem that can play a key role in identifying smaller portions of the training data.
We develop a novel factor 3-approximation algorithm to compute subsets based on the weighted sum of both k-center and uncertainty sampling objective functions.
arXiv Detail & Related papers (2023-12-17T04:41:07Z) - Central Similarity Multi-View Hashing for Multimedia Retrieval [14.766486538338498]
We present a novel Central Similarity Multi-View Hashing (CSMVH) method to address the mentioned problems.
On the MS COCO and NUS-WIDE, the proposed CSMVH performs better than the state-of-the-art methods by a large margin.
arXiv Detail & Related papers (2023-08-26T05:43:29Z) - Weighted Contrastive Hashing [11.14153532458873]
Unsupervised hash development has been hampered by insufficient data similarity mining based on global-only image representations.
We introduce a novel mutual attention module to alleviate the problem of information asymmetry in network features caused by the missing image structure.
The aggregated weighted similarities, which reflect the deep image relations, are distilled to facilitate the hash codes learning with a distillation loss.
arXiv Detail & Related papers (2022-09-28T13:47:33Z) - CgAT: Center-Guided Adversarial Training for Deep Hashing-Based
Retrieval [12.421908811085627]
We present a min-max based Center-guided Adversarial Training, namely CgAT, to improve the iteration of deep hashing networks.
CgAT learns to mitigate the effects of adversarial samples by minimizing the Hamming distance to the center codes.
Compared with the current state-of-the-art defense method, we significantly improve the defense performance by an average of 18.61%.
arXiv Detail & Related papers (2022-04-18T04:51:08Z) - LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of
Feature Similarity [49.84167231111667]
Existing works in self-supervised landmark detection are based on learning dense (pixel-level) feature representations from an image.
We introduce an approach to enhance the learning of dense equivariant representations in a self-supervised fashion.
We show that having such a prior in the feature extractor helps in landmark detection, even under drastically limited number of annotations.
arXiv Detail & Related papers (2022-04-06T17:48:18Z) - Improved Deep Classwise Hashing With Centers Similarity Learning for
Image Retrieval [19.052163348920512]
We propose an improved deep classwise hashing, which enables hashing learning and class centers learning simultaneously.
The proposed method effectively surpasses the original method and outperforms state-of-the-art baselines.
arXiv Detail & Related papers (2021-03-17T05:01:13Z) - Determinantal consensus clustering [77.34726150561087]
We propose the use of determinantal point processes or DPP for the random restart of clustering algorithms.
DPPs favor diversity of the center points within subsets.
We show through simulations that, contrary to DPP, this technique fails both to ensure diversity, and to obtain a good coverage of all data facets.
arXiv Detail & Related papers (2021-02-07T23:48:24Z) - Attention-based Saliency Hashing for Ophthalmic Image Retrieval [7.6609890269360505]
We propose Attention-based Saliency Hashing (ASH) for learning compact hash-code to represent ophthalmic images.
ASH embeds a spatial-attention module to focus more on the representation of salient regions.
ASH can further improve the retrieval performance compared to the state-of-the-art deep hashing methods.
arXiv Detail & Related papers (2020-12-07T06:04:12Z) - CIMON: Towards High-quality Hash Codes [63.37321228830102]
We propose a new method named textbfComprehensive stextbfImilarity textbfMining and ctextbfOnsistency leartextbfNing (CIMON)
First, we use global refinement and similarity statistical distribution to obtain reliable and smooth guidance. Second, both semantic and contrastive consistency learning are introduced to derive both disturb-invariant and discriminative hash codes.
arXiv Detail & Related papers (2020-10-15T14:47:14Z) - Reinforcing Short-Length Hashing [61.75883795807109]
Existing methods have poor performance in retrieval using an extremely short-length hash code.
In this study, we propose a novel reinforcing short-length hashing (RSLH)
In this proposed RSLH, mutual reconstruction between the hash representation and semantic labels is performed to preserve the semantic information.
Experiments on three large-scale image benchmarks demonstrate the superior performance of RSLH under various short-length hashing scenarios.
arXiv Detail & Related papers (2020-04-24T02:23:52Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.