CVROApr 11, 2025

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

arXiv:2504.08531v22 citationsh-index: 35
Originality Incremental advance
AI Analysis

This work addresses the challenge of coherent image descriptions for agents in cluttered environments, representing an incremental advancement in captioning methods.

The paper tackles the problem of generating spatially coherent image captions by proposing a self-supervised method that fine-tunes existing captioning models using a consensus mechanism and contrastive learning, resulting in significant improvements in caption accuracy and consistency.

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/

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes