DEMO: A Statistical Perspective for Efficient Image-Text Matching

• URL: http://arxiv.org/abs/2405.11496v1
• Date: Sun, 19 May 2024 09:38:56 GMT
• Title: DEMO: A Statistical Perspective for Efficient Image-Text Matching
• Authors: Fan Zhang, Xian-Sheng Hua, Chong Chen, Xiao Luo,
• Abstract summary: We introduce Distribution-based Structure Mining with Consistency Learning (DEMO) for efficient image-text matching. DEMO characterizes each image using multiple augmented views, which are considered as samples drawn from its intrinsic semantic distribution. In addition, we introduce collaborative consistency learning which not only preserves the similarity structure in the Hamming space but also encourages consistency between retrieval distribution from different directions.
• Score: 32.256725860652914
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Image-text matching has been a long-standing problem, which seeks to connect vision and language through semantic understanding. Due to the capability to manage large-scale raw data, unsupervised hashing-based approaches have gained prominence recently. They typically construct a semantic similarity structure using the natural distance, which subsequently provides guidance to the model optimization process. However, the similarity structure could be biased at the boundaries of semantic distributions, causing error accumulation during sequential optimization. To tackle this, we introduce a novel hashing approach termed Distribution-based Structure Mining with Consistency Learning (DEMO) for efficient image-text matching. From a statistical view, DEMO characterizes each image using multiple augmented views, which are considered as samples drawn from its intrinsic semantic distribution. Then, we employ a non-parametric distribution divergence to ensure a robust and precise similarity structure. In addition, we introduce collaborative consistency learning which not only preserves the similarity structure in the Hamming space but also encourages consistency between retrieval distribution from different directions in a self-supervised manner. Through extensive experiments on three benchmark image-text matching datasets, we demonstrate that DEMO achieves superior performance compared with many state-of-the-art methods.

Related papers

• Unsupervised Representation Learning by Balanced Self Attention Matching [2.3020018305241337]
  We present a self-supervised method for embedding image features called BAM. We obtain rich representations and avoid feature collapse by minimizing a loss that matches these distributions to their globally balanced and entropy regularized version. We show competitive performance with leading methods on both semi-supervised and transfer-learning benchmarks.
  arXiv  Detail & Related papers  (2024-08-04T12:52:44Z)
• Sequential Visual and Semantic Consistency for Semi-supervised Text Recognition [56.968108142307976]
  Scene text recognition (STR) is a challenging task that requires large-scale annotated data for training. Most existing STR methods resort to synthetic data, which may introduce domain discrepancy and degrade the performance of STR models. This paper proposes a novel semi-supervised learning method for STR that incorporates word-level consistency regularization from both visual and semantic aspects.
  arXiv  Detail & Related papers  (2024-02-24T13:00:54Z)
• Dynamic Visual Semantic Sub-Embeddings and Fast Re-Ranking [0.5242869847419834]
  We propose a Dynamic Visual Semantic Sub-Embeddings framework (DVSE) to reduce the information entropy. To encourage the generated candidate embeddings to capture various semantic variations, we construct a mixed distribution. We compare the performance with existing set-based method using four image feature encoders and two text feature encoders on three benchmark datasets.
  arXiv  Detail & Related papers  (2023-09-15T04:39:11Z)
• Unsupervised Hashing with Semantic Concept Mining [37.215530006668935]
  In this work, we propose a novel Un Hashing with Semantic Mining Concept, calledCM, which leverages a. high-quality similarity matrix. With the semantic similarity matrix as guiding information, a novel hashing loss with a modified contrastive loss based regularization item is proposed to optimize the hashing network.
  arXiv  Detail & Related papers  (2022-09-23T08:25:24Z)
• Semantic Image Synthesis via Diffusion Models [159.4285444680301]
  Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in various image generation tasks. Recent work on semantic image synthesis mainly follows the emphde facto Generative Adversarial Nets (GANs)
  arXiv  Detail & Related papers  (2022-06-30T18:31:51Z)
• Marginal Contrastive Correspondence for Guided Image Generation [58.0605433671196]
  Exemplar-based image translation establishes dense correspondences between a conditional input and an exemplar from two different domains. Existing work builds the cross-domain correspondences implicitly by minimizing feature-wise distances across the two domains. We design a Marginal Contrastive Learning Network (MCL-Net) that explores contrastive learning to learn domain-invariant features for realistic exemplar-based image translation.
  arXiv  Detail & Related papers  (2022-04-01T13:55:44Z)
• Image Synthesis via Semantic Composition [74.68191130898805]
  We present a novel approach to synthesize realistic images based on their semantic layouts. It hypothesizes that for objects with similar appearance, they share similar representation. Our method establishes dependencies between regions according to their appearance correlation, yielding both spatially variant and associated representations.
  arXiv  Detail & Related papers  (2021-09-15T02:26:07Z)
• Diverse Semantic Image Synthesis via Probability Distribution Modeling [103.88931623488088]
  We propose a novel diverse semantic image synthesis framework. Our method can achieve superior diversity and comparable quality compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-03-11T18:59:25Z)
• Beyond the Deep Metric Learning: Enhance the Cross-Modal Matching with Adversarial Discriminative Domain Regularization [21.904563910555368]
  We propose a novel learning framework to construct a set of discriminative data domains within each image-text pairs. Our approach can generally improve the learning efficiency and the performance of existing metrics learning frameworks.
  arXiv  Detail & Related papers  (2020-10-23T01:48:37Z)
• Out-of-distribution Generalization via Partial Feature Decorrelation [72.96261704851683]
  We present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimize a feature decomposition network and the target image classification model. The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.
  arXiv  Detail & Related papers  (2020-07-30T05:48:48Z)

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.