How Semantically Informative is an Image?: Measuring the Covariance-Weighted Norm of Contrastive Learning Embeddings

• URL: http://arxiv.org/abs/2506.22881v1
• Date: Sat, 28 Jun 2025 13:36:44 GMT
• Title: How Semantically Informative is an Image?: Measuring the Covariance-Weighted Norm of Contrastive Learning Embeddings
• Authors: Fumiya Uchiyama, Rintaro Yanagi, Shohei Taniguchi, Shota Takashiro, Masahiro Suzuki, Hirokatsu Kataoka, Yusuke Iwasawa, Yutaka Matsuo,
• Abstract summary: We introduce a semantic informativeness metric for an image calculated from text samples via a contrastive learning model.<n>Our metric quantifies how conditioning on an image distorts the distribution of associated texts.
• Score: 29.802362373605263
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Contrastive learning has the capacity to model multimodal probability distributions by embedding and aligning visual representations with semantics from captions. This approach enables the estimation of relational semantic similarity; however, it remains unclear whether it can also represent absolute semantic informativeness. In this work, we introduce a semantic informativeness metric for an image calculated from text samples via a contrastive learning model; similarly, the informativeness of a text is calculated from image samples. We propose a redefinition of the concept of Information Gain, a concept previously explored in natural language processing, extending its application to the domains of vision and language. Our metric quantifies how conditioning on an image distorts the distribution of associated texts, and vice versa for text conditioning on image distributions. In OpenCLIP's empirical results, we observe that images with the lowest Information Gain scores often correspond to placeholder icons such as "image not found." Furthermore, we propose to measure a norm-based metric of the embedding to estimate the Information Gain, following the theoretical results for Skip-Gram with Negative Sampling (SGNS) word embedding. Information Gain can be measured using either CLIP or SigLIP, and the results demonstrate a strong correlation with a coefficient of determination ranging from 0.98 to 1.00. After obtaining the mean and the covariance of the sample embedding, the computational cost of this method is independent of the sample size, and it is compatible with publicly available, open-weight models.

Related papers

• A Bayesian Approach to Weakly-supervised Laparoscopic Image Segmentation [1.9639956888747314]
  We study weakly-supervised laparoscopic image segmentation with sparse annotations. We introduce a novel Bayesian deep learning approach designed to enhance both the accuracy and interpretability of the model's segmentation.
  arXiv  Detail & Related papers  (2024-10-11T04:19:48Z)
• Explainable Metric Learning for Deflating Data Bias [2.977255700811213]
  We present an explainable metric learning framework, which constructs hierarchical levels of semantic segments of an image for better interpretability. Our approach enables a more human-understandable similarity measurement between two images based on the semantic segments within it.
  arXiv  Detail & Related papers  (2024-07-05T21:07:27Z)
• Semantic Approach to Quantifying the Consistency of Diffusion Model Image Generation [0.40792653193642503]
  We identify the need for an interpretable, quantitative score of the repeatability, or consistency, of image generation in diffusion models. We propose a semantic approach, using a pairwise mean CLIP score as our semantic consistency score.
  arXiv  Detail & Related papers  (2024-04-12T20:16:03Z)
• Introspective Deep Metric Learning [91.47907685364036]
  We propose an introspective deep metric learning framework for uncertainty-aware comparisons of images. The proposed IDML framework improves the performance of deep metric learning through uncertainty modeling.
  arXiv  Detail & Related papers  (2023-09-11T16:21:13Z)
• Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation [47.40949434032489]
  We propose a new contrastive-based evaluation metric for image captioning, namely Positive-Augmented Contrastive learning Score (PAC-S) PAC-S unifies the learning of a contrastive visual-semantic space with the addition of generated images and text on curated data. Experiments spanning several datasets demonstrate that our new metric achieves the highest correlation with human judgments on both images and videos.
  arXiv  Detail & Related papers  (2023-03-21T18:03:14Z)
• Semantic Image Synthesis via Diffusion Models [174.24523061460704]
  Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in various image generation tasks.<n>Recent work on semantic image synthesis mainly follows the de facto GAN-based approaches.<n>We propose a novel framework based on DDPM for semantic image synthesis.
  arXiv  Detail & Related papers  (2022-06-30T18:31:51Z)
• Introspective Deep Metric Learning for Image Retrieval [80.29866561553483]
  We argue that a good similarity model should consider the semantic discrepancies with caution to better deal with ambiguous images for more robust training. We propose to represent an image using not only a semantic embedding but also an accompanying uncertainty embedding, which describes the semantic characteristics and ambiguity of an image, respectively. The proposed IDML framework improves the performance of deep metric learning through uncertainty modeling and attains state-of-the-art results on the widely used CUB-200-2011, Cars196, and Stanford Online Products datasets.
  arXiv  Detail & Related papers  (2022-05-09T17:51:44Z)
• Deep Relational Metric Learning [84.95793654872399]
  This paper presents a deep relational metric learning framework for image clustering and retrieval. We learn an ensemble of features that characterizes an image from different aspects to model both interclass and intraclass distributions. Experiments on the widely-used CUB-200-2011, Cars196, and Stanford Online Products datasets demonstrate that our framework improves existing deep metric learning methods and achieves very competitive results.
  arXiv  Detail & Related papers  (2021-08-23T09:31:18Z)
• Consensus-Aware Visual-Semantic Embedding for Image-Text Matching [69.34076386926984]
  Image-text matching plays a central role in bridging vision and language. Most existing approaches only rely on the image-text instance pair to learn their representations. We propose a Consensus-aware Visual-Semantic Embedding model to incorporate the consensus information.
  arXiv  Detail & Related papers  (2020-07-17T10:22:57Z)
• Learning Representations by Predicting Bags of Visual Words [55.332200948110895]
  Self-supervised representation learning targets to learn convnet-based image representations from unlabeled data. Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially dense image descriptions.
  arXiv  Detail & Related papers  (2020-02-27T16:45:25Z)

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.