Embodied Image Captioning: Self-supervised Learning Agents for Spatially Coherent Image Descriptions

• URL: http://arxiv.org/abs/2504.08531v1
• Date: Fri, 11 Apr 2025 13:41:17 GMT
• Title: Embodied Image Captioning: Self-supervised Learning Agents for Spatially Coherent Image Descriptions
• Authors: Tommaso Galliena, Tommaso Apicella, Stefano Rosa, Pietro Morerio, Alessio Del Bue, Lorenzo Natale,
• Abstract summary: We propose a three-phase framework to fine-tune existing captioning models.<n>First, an agent explores the environment, collecting noisy image-caption pairs.<n>Then, a consistent pseudo-caption for each object instance is distilled via consensus.<n>Finally, these pseudo-captions are used to fine-tune an off-the-shelf captioning model.
• Score: 21.940022070054273
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a self-supervised method to improve an agent's abilities in describing arbitrary objects while actively exploring a generic environment. This is a challenging problem, as current models struggle to obtain coherent image captions due to different camera viewpoints and clutter. We propose a three-phase framework to fine-tune existing captioning models that enhances caption accuracy and consistency across views via a consensus mechanism. First, an agent explores the environment, collecting noisy image-caption pairs. Then, a consistent pseudo-caption for each object instance is distilled via consensus using a large language model. Finally, these pseudo-captions are used to fine-tune an off-the-shelf captioning model, with the addition of contrastive learning. We analyse the performance of the combination of captioning models, exploration policies, pseudo-labeling methods, and fine-tuning strategies, on our manually labeled test set. Results show that a policy can be trained to mine samples with higher disagreement compared to classical baselines. Our pseudo-captioning method, in combination with all policies, has a higher semantic similarity compared to other existing methods, and fine-tuning improves caption accuracy and consistency by a significant margin. Code and test set annotations available at https://hsp-iit.github.io/embodied-captioning/

Related papers

• Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning [71.14084801851381]
  Change captioning aims to succinctly describe the semantic change between a pair of similar images. Most existing methods directly capture the difference between them, which risk obtaining error-prone difference features. We propose a distractors-immune representation learning network that correlates the corresponding channels of two image representations.
  arXiv  Detail & Related papers  (2024-07-16T13:00:33Z)
• DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations [64.43387739794531]
  Current encoder-based approaches significantly impair the text controllability of text-to-image models while transferring styles. We introduce DEADiff to address this issue using the following two strategies. DEAiff attains the best visual stylization results and optimal balance between the text controllability inherent in the text-to-image model and style similarity to the reference image.
  arXiv  Detail & Related papers  (2024-03-11T17:35:23Z)
• Improving Image Captioning Descriptiveness by Ranking and LLM-based Fusion [17.99150939602917]
  State-of-The-Art (SoTA) image captioning models often rely on the Microsoft COCO (MS-COCO) dataset for training. We present a novel approach to address previous challenges by showcasing how captions generated from different SoTA models can be effectively fused.
  arXiv  Detail & Related papers  (2023-06-20T15:13:02Z)
• Neighborhood Contrastive Transformer for Change Captioning [80.10836469177185]
  We propose a neighborhood contrastive transformer to improve the model's perceiving ability for various changes under different scenes. The proposed method achieves the state-of-the-art performance on three public datasets with different change scenarios.
  arXiv  Detail & Related papers  (2023-03-06T14:39:54Z)
• Transform, Contrast and Tell: Coherent Entity-Aware Multi-Image Captioning [0.65268245109828]
  Coherent entity-aware multi-image captioning aims to generate coherent captions for neighboring images in a news document. This paper proposes a coherent entity-aware multi-image captioning model by making use of coherence relationships.
  arXiv  Detail & Related papers  (2023-02-04T07:50:31Z)
• Contrastive Semantic Similarity Learning for Image Captioning Evaluation with Intrinsic Auto-encoder [52.42057181754076]
  Motivated by the auto-encoder mechanism and contrastive representation learning advances, we propose a learning-based metric for image captioning. We develop three progressive model structures to learn the sentence level representations. Experiment results show that our proposed method can align well with the scores generated from other contemporary metrics.
  arXiv  Detail & Related papers  (2021-06-29T12:27:05Z)
• MOC-GAN: Mixing Objects and Captions to Generate Realistic Images [21.240099965546637]
  We introduce a more rational setting, generating a realistic image from the objects and captions. Under this setting, objects explicitly define the critical roles in the targeted images and captions implicitly describe their rich attributes and connections. A MOC-GAN is proposed to mix the inputs of two modalities to generate realistic images.
  arXiv  Detail & Related papers  (2021-06-06T14:04:07Z)
• 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)
• Intrinsic Image Captioning Evaluation [53.51379676690971]
  We propose a learning based metrics for image captioning, which we call Intrinsic Image Captioning Evaluation(I2CE) Experiment results show that our proposed method can keep robust performance and give more flexible scores to candidate captions when encountered with semantic similar expression or less aligned semantics.
  arXiv  Detail & Related papers  (2020-12-14T08:36:05Z)

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.